Add files using upload-large-folder tool

checkpoint-10032/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10032/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-10032/chat_template.jinja

@@ -0,0 +1,186 @@
+{{ bos_token }}{% if documents %}
+{% set tools = [] %}
+{%- macro document_turn(documents) -%}
+{# format documents into chat turn #}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[
+    {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+    {
+        "tool_call_id": "0",
+        "results": {
+{% for doc in documents %}
+            "{{ loop.index0 }}": {{doc|tojson}}{% if not loop.last %},
+            {% endif %}
+{% endfor %}
+
+        },
+        "is_error": null
+    }
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}
+{%- macro tool_call_id_to_int(messages, tool_call_id) %}
+{%- set counter = namespace(value=0) %}
+{%- set tool_call_id_seen = namespace(value=false) %}
+{%- for msg in messages %}
+    {%- if msg.tool_calls %}
+        {%- for tool_call in msg.tool_calls %}
+            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}
+                {{ counter.value }}
+                {%- set tool_call_id_seen.value = true %}
+            {%- endif %}
+            {%- set counter.value = counter.value + 1 %}
+        {%- endfor %}
+    {%- endif %}
+{%- endfor %}
+{%- endmacro %}
+{%- macro format_tool_message(messages, tool_msg) -%}
+{# format tool message #}
+    {
+        "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}",
+        "results": {
+            "0": {{ tool_msg.content|tojson }}
+        },
+        "is_error": null
+    }
+{%- endmacro -%}
+{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}
+{%- set tool_idx = namespace(value=0) %}
+{%- set tool_ids_seen = namespace(value=[]) %}
+{%- set sent_documents = namespace(value=false) %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
+You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
+
+Your information cutoff date is June 2024.
+
+You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
+{% if tools or documents %}
+
+You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
+
+## Tool Use
+Think about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.
+
+0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.
+    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.
+
+Then carry out your plan by repeatedly executing the following steps.
+1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing "tool_name" and "parameters" fields.
+    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.
+2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.
+    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its "tool_call_id".
+3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.
+    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.
+
+You can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.
+
+4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.
+{% if enable_citations %}
+
+## Grounding
+Importantly, note that "Reflection" and "Response" above can be grounded.
+Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".
+{% endif %}
+
+## Available Tools
+Here is the list of tools that you have available to you.
+You can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.
+Each tool is represented as a JSON object with fields like "name", "description", "parameters" (per JSON Schema), and optionally, "responses" (per JSON Schema).
+
+```json
+[
+{% if documents %}
+    {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}}{%- if tools %},{% endif %}
+
+{% endif %}
+{% for tool in tools %}
+    {"name": "{{ tool['function']['name'] }}", "description": "{{tool['function']['description']}}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null}{%- if not loop.last %},{% endif %}
+
+{% endfor %}
+]
+```
+
+{% endif %}
+# Default Preamble
+The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
+- Your name is Command.
+- You are a large language model built by Cohere.
+- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
+- If the input is ambiguous, ask clarifying follow-up questions.
+- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
+- Use LaTeX to generate mathematical notation for complex equations.
+- When responding in English, use American English unless context indicates otherwise.
+- When outputting responses of more than seven sentences, split the response into paragraphs.
+- Prefer the active voice.
+- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
+- Use gender-neutral pronouns for unspecified persons.
+- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
+- Use the third person when asked to write a summary.
+- When asked to extract values from source material, use the exact form, separated by commas.
+- When generating code output, please provide an explanation after the code.
+- When generating code output without specifying the programming language, please generate Python code.
+- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.
+{%- if developer_preamble %}
+
+
+# Developer Preamble
+The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
+{{ developer_preamble }}
+{%- endif -%}
+<|END_OF_TURN_TOKEN|>
+{%- for message in messages %}
+    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>
+    {%- elif message.role|lower == 'user' %}
+<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}
+    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[
+    {% for tc in message.tool_calls %}
+    {"tool_call_id": "{{ tool_idx.value }}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}
+
+    {% set tool_idx.value = tool_idx.value + 1 %}
+    {% endfor %}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}
+    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+{{ format_tool_message(messages, message) }}
+    {%- for msg in messages[loop.index0 + 1:] %}
+        {%- if msg.role|lower == 'tool' %},
+{{ format_tool_message(messages, msg) }}
+            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}
+        {%- else %}
+            {%- break %}
+        {%- endif %}
+    {%- endfor %}
+
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>
+    {%- endif %}
+{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+{%- else -%}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}
+    {%- set system_message = messages[0]['content'] %}{% elif false == true %}
+    {%- set loop_messages = messages %}{% set system_message = '' %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- set system_message = false %}
+{%- endif %}
+{%- if system_message != false -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
+{%- else -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|>' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+    {%- set content = message['content'] -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
+    {%- elif message['role'] == 'assistant' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>'  + content.strip() + '<|END_RESPONSE|><|END_OF_TURN_TOKEN|>' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt -%}
+    {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>' }}
+{%- endif %}
+{% endif %}

checkpoint-10032/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10032/tokenizer_config.json

@@ -0,0 +1,353 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255022": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255023": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

checkpoint-10112/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10112/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-10112/chat_template.jinja

@@ -0,0 +1,186 @@
+{{ bos_token }}{% if documents %}
+{% set tools = [] %}
+{%- macro document_turn(documents) -%}
+{# format documents into chat turn #}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[
+    {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+    {
+        "tool_call_id": "0",
+        "results": {
+{% for doc in documents %}
+            "{{ loop.index0 }}": {{doc|tojson}}{% if not loop.last %},
+            {% endif %}
+{% endfor %}
+
+        },
+        "is_error": null
+    }
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}
+{%- macro tool_call_id_to_int(messages, tool_call_id) %}
+{%- set counter = namespace(value=0) %}
+{%- set tool_call_id_seen = namespace(value=false) %}
+{%- for msg in messages %}
+    {%- if msg.tool_calls %}
+        {%- for tool_call in msg.tool_calls %}
+            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}
+                {{ counter.value }}
+                {%- set tool_call_id_seen.value = true %}
+            {%- endif %}
+            {%- set counter.value = counter.value + 1 %}
+        {%- endfor %}
+    {%- endif %}
+{%- endfor %}
+{%- endmacro %}
+{%- macro format_tool_message(messages, tool_msg) -%}
+{# format tool message #}
+    {
+        "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}",
+        "results": {
+            "0": {{ tool_msg.content|tojson }}
+        },
+        "is_error": null
+    }
+{%- endmacro -%}
+{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}
+{%- set tool_idx = namespace(value=0) %}
+{%- set tool_ids_seen = namespace(value=[]) %}
+{%- set sent_documents = namespace(value=false) %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
+You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
+
+Your information cutoff date is June 2024.
+
+You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
+{% if tools or documents %}
+
+You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
+
+## Tool Use
+Think about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.
+
+0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.
+    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.
+
+Then carry out your plan by repeatedly executing the following steps.
+1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing "tool_name" and "parameters" fields.
+    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.
+2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.
+    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its "tool_call_id".
+3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.
+    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.
+
+You can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.
+
+4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.
+{% if enable_citations %}
+
+## Grounding
+Importantly, note that "Reflection" and "Response" above can be grounded.
+Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".
+{% endif %}
+
+## Available Tools
+Here is the list of tools that you have available to you.
+You can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.
+Each tool is represented as a JSON object with fields like "name", "description", "parameters" (per JSON Schema), and optionally, "responses" (per JSON Schema).
+
+```json
+[
+{% if documents %}
+    {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}}{%- if tools %},{% endif %}
+
+{% endif %}
+{% for tool in tools %}
+    {"name": "{{ tool['function']['name'] }}", "description": "{{tool['function']['description']}}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null}{%- if not loop.last %},{% endif %}
+
+{% endfor %}
+]
+```
+
+{% endif %}
+# Default Preamble
+The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
+- Your name is Command.
+- You are a large language model built by Cohere.
+- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
+- If the input is ambiguous, ask clarifying follow-up questions.
+- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
+- Use LaTeX to generate mathematical notation for complex equations.
+- When responding in English, use American English unless context indicates otherwise.
+- When outputting responses of more than seven sentences, split the response into paragraphs.
+- Prefer the active voice.
+- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
+- Use gender-neutral pronouns for unspecified persons.
+- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
+- Use the third person when asked to write a summary.
+- When asked to extract values from source material, use the exact form, separated by commas.
+- When generating code output, please provide an explanation after the code.
+- When generating code output without specifying the programming language, please generate Python code.
+- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.
+{%- if developer_preamble %}
+
+
+# Developer Preamble
+The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
+{{ developer_preamble }}
+{%- endif -%}
+<|END_OF_TURN_TOKEN|>
+{%- for message in messages %}
+    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>
+    {%- elif message.role|lower == 'user' %}
+<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}
+    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[
+    {% for tc in message.tool_calls %}
+    {"tool_call_id": "{{ tool_idx.value }}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}
+
+    {% set tool_idx.value = tool_idx.value + 1 %}
+    {% endfor %}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}
+    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+{{ format_tool_message(messages, message) }}
+    {%- for msg in messages[loop.index0 + 1:] %}
+        {%- if msg.role|lower == 'tool' %},
+{{ format_tool_message(messages, msg) }}
+            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}
+        {%- else %}
+            {%- break %}
+        {%- endif %}
+    {%- endfor %}
+
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>
+    {%- endif %}
+{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+{%- else -%}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}
+    {%- set system_message = messages[0]['content'] %}{% elif false == true %}
+    {%- set loop_messages = messages %}{% set system_message = '' %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- set system_message = false %}
+{%- endif %}
+{%- if system_message != false -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
+{%- else -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|>' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+    {%- set content = message['content'] -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
+    {%- elif message['role'] == 'assistant' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>'  + content.strip() + '<|END_RESPONSE|><|END_OF_TURN_TOKEN|>' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt -%}
+    {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>' }}
+{%- endif %}
+{% endif %}

checkpoint-10112/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10112/tokenizer_config.json

@@ -0,0 +1,353 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255022": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255023": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

checkpoint-10128/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10128/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-10128/chat_template.jinja

@@ -0,0 +1,186 @@
+{{ bos_token }}{% if documents %}
+{% set tools = [] %}
+{%- macro document_turn(documents) -%}
+{# format documents into chat turn #}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[
+    {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+    {
+        "tool_call_id": "0",
+        "results": {
+{% for doc in documents %}
+            "{{ loop.index0 }}": {{doc|tojson}}{% if not loop.last %},
+            {% endif %}
+{% endfor %}
+
+        },
+        "is_error": null
+    }
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}
+{%- macro tool_call_id_to_int(messages, tool_call_id) %}
+{%- set counter = namespace(value=0) %}
+{%- set tool_call_id_seen = namespace(value=false) %}
+{%- for msg in messages %}
+    {%- if msg.tool_calls %}
+        {%- for tool_call in msg.tool_calls %}
+            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}
+                {{ counter.value }}
+                {%- set tool_call_id_seen.value = true %}
+            {%- endif %}
+            {%- set counter.value = counter.value + 1 %}
+        {%- endfor %}
+    {%- endif %}
+{%- endfor %}
+{%- endmacro %}
+{%- macro format_tool_message(messages, tool_msg) -%}
+{# format tool message #}
+    {
+        "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}",
+        "results": {
+            "0": {{ tool_msg.content|tojson }}
+        },
+        "is_error": null
+    }
+{%- endmacro -%}
+{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}
+{%- set tool_idx = namespace(value=0) %}
+{%- set tool_ids_seen = namespace(value=[]) %}
+{%- set sent_documents = namespace(value=false) %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
+You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
+
+Your information cutoff date is June 2024.
+
+You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
+{% if tools or documents %}
+
+You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
+
+## Tool Use
+Think about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.
+
+0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.
+    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.
+
+Then carry out your plan by repeatedly executing the following steps.
+1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing "tool_name" and "parameters" fields.
+    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.
+2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.
+    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its "tool_call_id".
+3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.
+    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.
+
+You can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.
+
+4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.
+{% if enable_citations %}
+
+## Grounding
+Importantly, note that "Reflection" and "Response" above can be grounded.
+Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".
+{% endif %}
+
+## Available Tools
+Here is the list of tools that you have available to you.
+You can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.
+Each tool is represented as a JSON object with fields like "name", "description", "parameters" (per JSON Schema), and optionally, "responses" (per JSON Schema).
+
+```json
+[
+{% if documents %}
+    {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}}{%- if tools %},{% endif %}
+
+{% endif %}
+{% for tool in tools %}
+    {"name": "{{ tool['function']['name'] }}", "description": "{{tool['function']['description']}}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null}{%- if not loop.last %},{% endif %}
+
+{% endfor %}
+]
+```
+
+{% endif %}
+# Default Preamble
+The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
+- Your name is Command.
+- You are a large language model built by Cohere.
+- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
+- If the input is ambiguous, ask clarifying follow-up questions.
+- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
+- Use LaTeX to generate mathematical notation for complex equations.
+- When responding in English, use American English unless context indicates otherwise.
+- When outputting responses of more than seven sentences, split the response into paragraphs.
+- Prefer the active voice.
+- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
+- Use gender-neutral pronouns for unspecified persons.
+- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
+- Use the third person when asked to write a summary.
+- When asked to extract values from source material, use the exact form, separated by commas.
+- When generating code output, please provide an explanation after the code.
+- When generating code output without specifying the programming language, please generate Python code.
+- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.
+{%- if developer_preamble %}
+
+
+# Developer Preamble
+The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
+{{ developer_preamble }}
+{%- endif -%}
+<|END_OF_TURN_TOKEN|>
+{%- for message in messages %}
+    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>
+    {%- elif message.role|lower == 'user' %}
+<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}
+    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[
+    {% for tc in message.tool_calls %}
+    {"tool_call_id": "{{ tool_idx.value }}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}
+
+    {% set tool_idx.value = tool_idx.value + 1 %}
+    {% endfor %}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}
+    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+{{ format_tool_message(messages, message) }}
+    {%- for msg in messages[loop.index0 + 1:] %}
+        {%- if msg.role|lower == 'tool' %},
+{{ format_tool_message(messages, msg) }}
+            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}
+        {%- else %}
+            {%- break %}
+        {%- endif %}
+    {%- endfor %}
+
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>
+    {%- endif %}
+{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+{%- else -%}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}
+    {%- set system_message = messages[0]['content'] %}{% elif false == true %}
+    {%- set loop_messages = messages %}{% set system_message = '' %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- set system_message = false %}
+{%- endif %}
+{%- if system_message != false -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
+{%- else -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|>' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+    {%- set content = message['content'] -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
+    {%- elif message['role'] == 'assistant' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>'  + content.strip() + '<|END_RESPONSE|><|END_OF_TURN_TOKEN|>' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt -%}
+    {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>' }}
+{%- endif %}
+{% endif %}

checkpoint-10128/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10128/tokenizer_config.json

@@ -0,0 +1,353 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255022": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255023": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

checkpoint-10416/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10416/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-10416/chat_template.jinja

@@ -0,0 +1,186 @@
+{{ bos_token }}{% if documents %}
+{% set tools = [] %}
+{%- macro document_turn(documents) -%}
+{# format documents into chat turn #}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[
+    {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+    {
+        "tool_call_id": "0",
+        "results": {
+{% for doc in documents %}
+            "{{ loop.index0 }}": {{doc|tojson}}{% if not loop.last %},
+            {% endif %}
+{% endfor %}
+
+        },
+        "is_error": null
+    }
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}
+{%- macro tool_call_id_to_int(messages, tool_call_id) %}
+{%- set counter = namespace(value=0) %}
+{%- set tool_call_id_seen = namespace(value=false) %}
+{%- for msg in messages %}
+    {%- if msg.tool_calls %}
+        {%- for tool_call in msg.tool_calls %}
+            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}
+                {{ counter.value }}
+                {%- set tool_call_id_seen.value = true %}
+            {%- endif %}
+            {%- set counter.value = counter.value + 1 %}
+        {%- endfor %}
+    {%- endif %}
+{%- endfor %}
+{%- endmacro %}
+{%- macro format_tool_message(messages, tool_msg) -%}
+{# format tool message #}
+    {
+        "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}",
+        "results": {
+            "0": {{ tool_msg.content|tojson }}
+        },
+        "is_error": null
+    }
+{%- endmacro -%}
+{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}
+{%- set tool_idx = namespace(value=0) %}
+{%- set tool_ids_seen = namespace(value=[]) %}
+{%- set sent_documents = namespace(value=false) %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
+You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
+
+Your information cutoff date is June 2024.
+
+You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
+{% if tools or documents %}
+
+You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
+
+## Tool Use
+Think about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.
+
+0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.
+    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.
+
+Then carry out your plan by repeatedly executing the following steps.
+1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing "tool_name" and "parameters" fields.
+    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.
+2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.
+    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its "tool_call_id".
+3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.
+    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.
+
+You can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.
+
+4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.
+{% if enable_citations %}
+
+## Grounding
+Importantly, note that "Reflection" and "Response" above can be grounded.
+Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".
+{% endif %}
+
+## Available Tools
+Here is the list of tools that you have available to you.
+You can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.
+Each tool is represented as a JSON object with fields like "name", "description", "parameters" (per JSON Schema), and optionally, "responses" (per JSON Schema).
+
+```json
+[
+{% if documents %}
+    {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}}{%- if tools %},{% endif %}
+
+{% endif %}
+{% for tool in tools %}
+    {"name": "{{ tool['function']['name'] }}", "description": "{{tool['function']['description']}}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null}{%- if not loop.last %},{% endif %}
+
+{% endfor %}
+]
+```
+
+{% endif %}
+# Default Preamble
+The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
+- Your name is Command.
+- You are a large language model built by Cohere.
+- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
+- If the input is ambiguous, ask clarifying follow-up questions.
+- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
+- Use LaTeX to generate mathematical notation for complex equations.
+- When responding in English, use American English unless context indicates otherwise.
+- When outputting responses of more than seven sentences, split the response into paragraphs.
+- Prefer the active voice.
+- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
+- Use gender-neutral pronouns for unspecified persons.
+- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
+- Use the third person when asked to write a summary.
+- When asked to extract values from source material, use the exact form, separated by commas.
+- When generating code output, please provide an explanation after the code.
+- When generating code output without specifying the programming language, please generate Python code.
+- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.
+{%- if developer_preamble %}
+
+
+# Developer Preamble
+The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
+{{ developer_preamble }}
+{%- endif -%}
+<|END_OF_TURN_TOKEN|>
+{%- for message in messages %}
+    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>
+    {%- elif message.role|lower == 'user' %}
+<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}
+    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[
+    {% for tc in message.tool_calls %}
+    {"tool_call_id": "{{ tool_idx.value }}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}
+
+    {% set tool_idx.value = tool_idx.value + 1 %}
+    {% endfor %}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}
+    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+{{ format_tool_message(messages, message) }}
+    {%- for msg in messages[loop.index0 + 1:] %}
+        {%- if msg.role|lower == 'tool' %},
+{{ format_tool_message(messages, msg) }}
+            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}
+        {%- else %}
+            {%- break %}
+        {%- endif %}
+    {%- endfor %}
+
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>
+    {%- endif %}
+{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+{%- else -%}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}
+    {%- set system_message = messages[0]['content'] %}{% elif false == true %}
+    {%- set loop_messages = messages %}{% set system_message = '' %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- set system_message = false %}
+{%- endif %}
+{%- if system_message != false -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
+{%- else -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|>' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+    {%- set content = message['content'] -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
+    {%- elif message['role'] == 'assistant' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>'  + content.strip() + '<|END_RESPONSE|><|END_OF_TURN_TOKEN|>' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt -%}
+    {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>' }}
+{%- endif %}
+{% endif %}

checkpoint-10416/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10416/tokenizer_config.json

@@ -0,0 +1,353 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255022": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255023": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

checkpoint-10432/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10432/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-10432/chat_template.jinja

@@ -0,0 +1,186 @@
+{{ bos_token }}{% if documents %}
+{% set tools = [] %}
+{%- macro document_turn(documents) -%}
+{# format documents into chat turn #}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[
+    {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+    {
+        "tool_call_id": "0",
+        "results": {
+{% for doc in documents %}
+            "{{ loop.index0 }}": {{doc|tojson}}{% if not loop.last %},
+            {% endif %}
+{% endfor %}
+
+        },
+        "is_error": null
+    }
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}
+{%- macro tool_call_id_to_int(messages, tool_call_id) %}
+{%- set counter = namespace(value=0) %}
+{%- set tool_call_id_seen = namespace(value=false) %}
+{%- for msg in messages %}
+    {%- if msg.tool_calls %}
+        {%- for tool_call in msg.tool_calls %}
+            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}
+                {{ counter.value }}
+                {%- set tool_call_id_seen.value = true %}
+            {%- endif %}
+            {%- set counter.value = counter.value + 1 %}
+        {%- endfor %}
+    {%- endif %}
+{%- endfor %}
+{%- endmacro %}
+{%- macro format_tool_message(messages, tool_msg) -%}
+{# format tool message #}
+    {
+        "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}",
+        "results": {
+            "0": {{ tool_msg.content|tojson }}
+        },
+        "is_error": null
+    }
+{%- endmacro -%}
+{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}
+{%- set tool_idx = namespace(value=0) %}
+{%- set tool_ids_seen = namespace(value=[]) %}
+{%- set sent_documents = namespace(value=false) %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
+You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
+
+Your information cutoff date is June 2024.
+
+You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
+{% if tools or documents %}
+
+You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
+
+## Tool Use
+Think about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.
+
+0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.
+    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.
+
+Then carry out your plan by repeatedly executing the following steps.
+1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing "tool_name" and "parameters" fields.
+    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.
+2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.
+    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its "tool_call_id".
+3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.
+    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.
+
+You can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.
+
+4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.
+{% if enable_citations %}
+
+## Grounding
+Importantly, note that "Reflection" and "Response" above can be grounded.
+Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".
+{% endif %}
+
+## Available Tools
+Here is the list of tools that you have available to you.
+You can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.
+Each tool is represented as a JSON object with fields like "name", "description", "parameters" (per JSON Schema), and optionally, "responses" (per JSON Schema).
+
+```json
+[
+{% if documents %}
+    {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}}{%- if tools %},{% endif %}
+
+{% endif %}
+{% for tool in tools %}
+    {"name": "{{ tool['function']['name'] }}", "description": "{{tool['function']['description']}}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null}{%- if not loop.last %},{% endif %}
+
+{% endfor %}
+]
+```
+
+{% endif %}
+# Default Preamble
+The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
+- Your name is Command.
+- You are a large language model built by Cohere.
+- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
+- If the input is ambiguous, ask clarifying follow-up questions.
+- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
+- Use LaTeX to generate mathematical notation for complex equations.
+- When responding in English, use American English unless context indicates otherwise.
+- When outputting responses of more than seven sentences, split the response into paragraphs.
+- Prefer the active voice.
+- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
+- Use gender-neutral pronouns for unspecified persons.
+- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
+- Use the third person when asked to write a summary.
+- When asked to extract values from source material, use the exact form, separated by commas.
+- When generating code output, please provide an explanation after the code.
+- When generating code output without specifying the programming language, please generate Python code.
+- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.
+{%- if developer_preamble %}
+
+
+# Developer Preamble
+The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
+{{ developer_preamble }}
+{%- endif -%}
+<|END_OF_TURN_TOKEN|>
+{%- for message in messages %}
+    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>
+    {%- elif message.role|lower == 'user' %}
+<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}
+    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[
+    {% for tc in message.tool_calls %}
+    {"tool_call_id": "{{ tool_idx.value }}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}
+
+    {% set tool_idx.value = tool_idx.value + 1 %}
+    {% endfor %}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}
+    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+{{ format_tool_message(messages, message) }}
+    {%- for msg in messages[loop.index0 + 1:] %}
+        {%- if msg.role|lower == 'tool' %},
+{{ format_tool_message(messages, msg) }}
+            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}
+        {%- else %}
+            {%- break %}
+        {%- endif %}
+    {%- endfor %}
+
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>
+    {%- endif %}
+{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+{%- else -%}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}
+    {%- set system_message = messages[0]['content'] %}{% elif false == true %}
+    {%- set loop_messages = messages %}{% set system_message = '' %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- set system_message = false %}
+{%- endif %}
+{%- if system_message != false -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
+{%- else -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|>' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+    {%- set content = message['content'] -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
+    {%- elif message['role'] == 'assistant' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>'  + content.strip() + '<|END_RESPONSE|><|END_OF_TURN_TOKEN|>' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt -%}
+    {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>' }}
+{%- endif %}
+{% endif %}

checkpoint-10432/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10432/tokenizer_config.json

@@ -0,0 +1,353 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255022": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255023": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

checkpoint-10448/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10448/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-10448/chat_template.jinja

@@ -0,0 +1,186 @@
+{{ bos_token }}{% if documents %}
+{% set tools = [] %}
+{%- macro document_turn(documents) -%}
+{# format documents into chat turn #}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[
+    {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+    {
+        "tool_call_id": "0",
+        "results": {
+{% for doc in documents %}
+            "{{ loop.index0 }}": {{doc|tojson}}{% if not loop.last %},
+            {% endif %}
+{% endfor %}
+
+        },
+        "is_error": null
+    }
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}
+{%- macro tool_call_id_to_int(messages, tool_call_id) %}
+{%- set counter = namespace(value=0) %}
+{%- set tool_call_id_seen = namespace(value=false) %}
+{%- for msg in messages %}
+    {%- if msg.tool_calls %}
+        {%- for tool_call in msg.tool_calls %}
+            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}
+                {{ counter.value }}
+                {%- set tool_call_id_seen.value = true %}
+            {%- endif %}
+            {%- set counter.value = counter.value + 1 %}
+        {%- endfor %}
+    {%- endif %}
+{%- endfor %}
+{%- endmacro %}
+{%- macro format_tool_message(messages, tool_msg) -%}
+{# format tool message #}
+    {
+        "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}",
+        "results": {
+            "0": {{ tool_msg.content|tojson }}
+        },
+        "is_error": null
+    }
+{%- endmacro -%}
+{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}
+{%- set tool_idx = namespace(value=0) %}
+{%- set tool_ids_seen = namespace(value=[]) %}
+{%- set sent_documents = namespace(value=false) %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
+You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
+
+Your information cutoff date is June 2024.
+
+You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
+{% if tools or documents %}
+
+You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
+
+## Tool Use
+Think about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.
+
+0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.
+    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.
+
+Then carry out your plan by repeatedly executing the following steps.
+1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing "tool_name" and "parameters" fields.
+    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.
+2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.
+    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its "tool_call_id".
+3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.
+    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.
+
+You can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.
+
+4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.
+{% if enable_citations %}
+
+## Grounding
+Importantly, note that "Reflection" and "Response" above can be grounded.
+Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".
+{% endif %}
+
+## Available Tools
+Here is the list of tools that you have available to you.
+You can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.
+Each tool is represented as a JSON object with fields like "name", "description", "parameters" (per JSON Schema), and optionally, "responses" (per JSON Schema).
+
+```json
+[
+{% if documents %}
+    {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}}{%- if tools %},{% endif %}
+
+{% endif %}
+{% for tool in tools %}
+    {"name": "{{ tool['function']['name'] }}", "description": "{{tool['function']['description']}}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null}{%- if not loop.last %},{% endif %}
+
+{% endfor %}
+]
+```
+
+{% endif %}
+# Default Preamble
+The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
+- Your name is Command.
+- You are a large language model built by Cohere.
+- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
+- If the input is ambiguous, ask clarifying follow-up questions.
+- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
+- Use LaTeX to generate mathematical notation for complex equations.
+- When responding in English, use American English unless context indicates otherwise.
+- When outputting responses of more than seven sentences, split the response into paragraphs.
+- Prefer the active voice.
+- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
+- Use gender-neutral pronouns for unspecified persons.
+- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
+- Use the third person when asked to write a summary.
+- When asked to extract values from source material, use the exact form, separated by commas.
+- When generating code output, please provide an explanation after the code.
+- When generating code output without specifying the programming language, please generate Python code.
+- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.
+{%- if developer_preamble %}
+
+
+# Developer Preamble
+The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
+{{ developer_preamble }}
+{%- endif -%}
+<|END_OF_TURN_TOKEN|>
+{%- for message in messages %}
+    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>
+    {%- elif message.role|lower == 'user' %}
+<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}
+    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[
+    {% for tc in message.tool_calls %}
+    {"tool_call_id": "{{ tool_idx.value }}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}
+
+    {% set tool_idx.value = tool_idx.value + 1 %}
+    {% endfor %}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}
+    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+{{ format_tool_message(messages, message) }}
+    {%- for msg in messages[loop.index0 + 1:] %}
+        {%- if msg.role|lower == 'tool' %},
+{{ format_tool_message(messages, msg) }}
+            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}
+        {%- else %}
+            {%- break %}
+        {%- endif %}
+    {%- endfor %}
+
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>
+    {%- endif %}
+{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+{%- else -%}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}
+    {%- set system_message = messages[0]['content'] %}{% elif false == true %}
+    {%- set loop_messages = messages %}{% set system_message = '' %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- set system_message = false %}
+{%- endif %}
+{%- if system_message != false -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
+{%- else -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|>' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+    {%- set content = message['content'] -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
+    {%- elif message['role'] == 'assistant' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>'  + content.strip() + '<|END_RESPONSE|><|END_OF_TURN_TOKEN|>' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt -%}
+    {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>' }}
+{%- endif %}
+{% endif %}

checkpoint-10448/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10448/tokenizer_config.json

@@ -0,0 +1,353 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255022": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255023": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

checkpoint-1056/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-1056/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1056/chat_template.jinja

@@ -0,0 +1,186 @@
+{{ bos_token }}{% if documents %}
+{% set tools = [] %}
+{%- macro document_turn(documents) -%}
+{# format documents into chat turn #}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[
+    {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+    {
+        "tool_call_id": "0",
+        "results": {
+{% for doc in documents %}
+            "{{ loop.index0 }}": {{doc|tojson}}{% if not loop.last %},
+            {% endif %}
+{% endfor %}
+
+        },
+        "is_error": null
+    }
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}
+{%- macro tool_call_id_to_int(messages, tool_call_id) %}
+{%- set counter = namespace(value=0) %}
+{%- set tool_call_id_seen = namespace(value=false) %}
+{%- for msg in messages %}
+    {%- if msg.tool_calls %}
+        {%- for tool_call in msg.tool_calls %}
+            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}
+                {{ counter.value }}
+                {%- set tool_call_id_seen.value = true %}
+            {%- endif %}
+            {%- set counter.value = counter.value + 1 %}
+        {%- endfor %}
+    {%- endif %}
+{%- endfor %}
+{%- endmacro %}
+{%- macro format_tool_message(messages, tool_msg) -%}
+{# format tool message #}
+    {
+        "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}",
+        "results": {
+            "0": {{ tool_msg.content|tojson }}
+        },
+        "is_error": null
+    }
+{%- endmacro -%}
+{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}
+{%- set tool_idx = namespace(value=0) %}
+{%- set tool_ids_seen = namespace(value=[]) %}
+{%- set sent_documents = namespace(value=false) %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
+You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
+
+Your information cutoff date is June 2024.
+
+You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
+{% if tools or documents %}
+
+You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
+
+## Tool Use
+Think about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.
+
+0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.
+    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.
+
+Then carry out your plan by repeatedly executing the following steps.
+1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing "tool_name" and "parameters" fields.
+    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.
+2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.
+    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its "tool_call_id".
+3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.
+    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.
+
+You can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.
+
+4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.
+{% if enable_citations %}
+
+## Grounding
+Importantly, note that "Reflection" and "Response" above can be grounded.
+Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".
+{% endif %}
+
+## Available Tools
+Here is the list of tools that you have available to you.
+You can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.
+Each tool is represented as a JSON object with fields like "name", "description", "parameters" (per JSON Schema), and optionally, "responses" (per JSON Schema).
+
+```json
+[
+{% if documents %}
+    {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}}{%- if tools %},{% endif %}
+
+{% endif %}
+{% for tool in tools %}
+    {"name": "{{ tool['function']['name'] }}", "description": "{{tool['function']['description']}}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null}{%- if not loop.last %},{% endif %}
+
+{% endfor %}
+]
+```
+
+{% endif %}
+# Default Preamble
+The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
+- Your name is Command.
+- You are a large language model built by Cohere.
+- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
+- If the input is ambiguous, ask clarifying follow-up questions.
+- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
+- Use LaTeX to generate mathematical notation for complex equations.
+- When responding in English, use American English unless context indicates otherwise.
+- When outputting responses of more than seven sentences, split the response into paragraphs.
+- Prefer the active voice.
+- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
+- Use gender-neutral pronouns for unspecified persons.
+- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
+- Use the third person when asked to write a summary.
+- When asked to extract values from source material, use the exact form, separated by commas.
+- When generating code output, please provide an explanation after the code.
+- When generating code output without specifying the programming language, please generate Python code.
+- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.
+{%- if developer_preamble %}
+
+
+# Developer Preamble
+The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
+{{ developer_preamble }}
+{%- endif -%}
+<|END_OF_TURN_TOKEN|>
+{%- for message in messages %}
+    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>
+    {%- elif message.role|lower == 'user' %}
+<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}
+    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[
+    {% for tc in message.tool_calls %}
+    {"tool_call_id": "{{ tool_idx.value }}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}
+
+    {% set tool_idx.value = tool_idx.value + 1 %}
+    {% endfor %}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}
+    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+{{ format_tool_message(messages, message) }}
+    {%- for msg in messages[loop.index0 + 1:] %}
+        {%- if msg.role|lower == 'tool' %},
+{{ format_tool_message(messages, msg) }}
+            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}
+        {%- else %}
+            {%- break %}
+        {%- endif %}
+    {%- endfor %}
+
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>
+    {%- endif %}
+{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+{%- else -%}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}
+    {%- set system_message = messages[0]['content'] %}{% elif false == true %}
+    {%- set loop_messages = messages %}{% set system_message = '' %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- set system_message = false %}
+{%- endif %}
+{%- if system_message != false -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
+{%- else -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|>' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+    {%- set content = message['content'] -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
+    {%- elif message['role'] == 'assistant' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>'  + content.strip() + '<|END_RESPONSE|><|END_OF_TURN_TOKEN|>' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt -%}
+    {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>' }}
+{%- endif %}
+{% endif %}

checkpoint-1056/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1056/tokenizer_config.json

@@ -0,0 +1,353 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255022": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255023": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

checkpoint-1056/trainer_state.json

@@ -0,0 +1,1820 @@
+{
+  "best_global_step": 352,
+  "best_metric": 1.5587613582611084,
+  "best_model_checkpoint": "./my_model/checkpoint-352",
+  "epoch": 66.0,
+  "eval_steps": 500,
+  "global_step": 1056,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.611812502145767,
+      "epoch": 0.06451612903225806,
+      "grad_norm": 2.948519468307495,
+      "learning_rate": 0.0,
+      "loss": 5.2626,
+      "mean_token_accuracy": 0.2785332165658474,
+      "num_tokens": 1354.0,
+      "step": 1
+    },
+    {
+      "entropy": 2.4764878584278955,
+      "epoch": 0.6451612903225806,
+      "grad_norm": 2.852177858352661,
+      "learning_rate": 5.625e-07,
+      "loss": 5.0479,
+      "mean_token_accuracy": 0.30352623243298793,
+      "num_tokens": 13915.0,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_entropy": 2.549605812345232,
+      "eval_loss": 5.082220554351807,
+      "eval_mean_token_accuracy": 0.29234256382499424,
+      "eval_num_tokens": 21527.0,
+      "eval_runtime": 0.8908,
+      "eval_samples_per_second": 61.741,
+      "eval_steps_per_second": 15.716,
+      "step": 16
+    },
+    {
+      "entropy": 2.4721337352928363,
+      "epoch": 1.2580645161290323,
+      "grad_norm": 2.8321847915649414,
+      "learning_rate": 1.1875e-06,
+      "loss": 5.033,
+      "mean_token_accuracy": 0.30711135052536664,
+      "num_tokens": 27177.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.514200139045715,
+      "epoch": 1.903225806451613,
+      "grad_norm": 3.025498151779175,
+      "learning_rate": 1.8125e-06,
+      "loss": 5.0773,
+      "mean_token_accuracy": 0.2981846956536174,
+      "num_tokens": 40986.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_entropy": 2.5709889445986067,
+      "eval_loss": 5.047023773193359,
+      "eval_mean_token_accuracy": 0.2919592655130795,
+      "eval_num_tokens": 43054.0,
+      "eval_runtime": 0.8868,
+      "eval_samples_per_second": 62.018,
+      "eval_steps_per_second": 15.786,
+      "step": 32
+    },
+    {
+      "entropy": 2.541774250959095,
+      "epoch": 2.5161290322580645,
+      "grad_norm": 3.4038965702056885,
+      "learning_rate": 2.4375000000000004e-06,
+      "loss": 5.0438,
+      "mean_token_accuracy": 0.2972054022707437,
+      "num_tokens": 54010.0,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "eval_entropy": 2.5724382059914723,
+      "eval_loss": 4.9238505363464355,
+      "eval_mean_token_accuracy": 0.2935441700475557,
+      "eval_num_tokens": 64581.0,
+      "eval_runtime": 0.997,
+      "eval_samples_per_second": 55.165,
+      "eval_steps_per_second": 14.042,
+      "step": 48
+    },
+    {
+      "entropy": 2.5254996732661597,
+      "epoch": 3.129032258064516,
+      "grad_norm": 4.6959710121154785,
+      "learning_rate": 3.0625e-06,
+      "loss": 4.8754,
+      "mean_token_accuracy": 0.3122231556396735,
+      "num_tokens": 67318.0,
+      "step": 50
+    },
+    {
+      "entropy": 2.532456985116005,
+      "epoch": 3.774193548387097,
+      "grad_norm": 1.8910281658172607,
+      "learning_rate": 3.6875e-06,
+      "loss": 4.8683,
+      "mean_token_accuracy": 0.31472160052508114,
+      "num_tokens": 81243.0,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 2.6716178315026418,
+      "eval_loss": 4.745687484741211,
+      "eval_mean_token_accuracy": 0.3186415561607906,
+      "eval_num_tokens": 86108.0,
+      "eval_runtime": 0.8831,
+      "eval_samples_per_second": 62.282,
+      "eval_steps_per_second": 15.854,
+      "step": 64
+    },
+    {
+      "entropy": 2.6316533935697457,
+      "epoch": 4.387096774193548,
+      "grad_norm": 1.985713243484497,
+      "learning_rate": 4.3125e-06,
+      "loss": 4.7158,
+      "mean_token_accuracy": 0.32339329899925934,
+      "num_tokens": 94546.0,
+      "step": 70
+    },
+    {
+      "entropy": 2.6654595481721977,
+      "epoch": 5.0,
+      "grad_norm": 1.8635355234146118,
+      "learning_rate": 4.937500000000001e-06,
+      "loss": 4.4521,
+      "mean_token_accuracy": 0.3342058395868854,
+      "num_tokens": 107635.0,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "eval_entropy": 2.7309968301228116,
+      "eval_loss": 4.356206893920898,
+      "eval_mean_token_accuracy": 0.3469075581857136,
+      "eval_num_tokens": 107635.0,
+      "eval_runtime": 1.4048,
+      "eval_samples_per_second": 39.153,
+      "eval_steps_per_second": 9.966,
+      "step": 80
+    },
+    {
+      "entropy": 2.6752349376678466,
+      "epoch": 5.645161290322581,
+      "grad_norm": 1.7081493139266968,
+      "learning_rate": 5.5625000000000005e-06,
+      "loss": 4.1996,
+      "mean_token_accuracy": 0.3722452763468027,
+      "num_tokens": 121563.0,
+      "step": 90
+    },
+    {
+      "epoch": 6.0,
+      "eval_entropy": 2.802973576954433,
+      "eval_loss": 3.9146478176116943,
+      "eval_mean_token_accuracy": 0.38693774597985403,
+      "eval_num_tokens": 129162.0,
+      "eval_runtime": 0.9423,
+      "eval_samples_per_second": 58.371,
+      "eval_steps_per_second": 14.858,
+      "step": 96
+    },
+    {
+      "entropy": 2.770364958988993,
+      "epoch": 6.258064516129032,
+      "grad_norm": 1.6673827171325684,
+      "learning_rate": 6.1875000000000005e-06,
+      "loss": 3.9392,
+      "mean_token_accuracy": 0.387496774133883,
+      "num_tokens": 134741.0,
+      "step": 100
+    },
+    {
+      "entropy": 2.7224088311195374,
+      "epoch": 6.903225806451613,
+      "grad_norm": 1.527048110961914,
+      "learning_rate": 6.8125e-06,
+      "loss": 3.62,
+      "mean_token_accuracy": 0.45071578361094,
+      "num_tokens": 148587.0,
+      "step": 110
+    },
+    {
+      "epoch": 7.0,
+      "eval_entropy": 2.6817347833088467,
+      "eval_loss": 3.47971248626709,
+      "eval_mean_token_accuracy": 0.487923339009285,
+      "eval_num_tokens": 150689.0,
+      "eval_runtime": 0.9499,
+      "eval_samples_per_second": 57.9,
+      "eval_steps_per_second": 14.738,
+      "step": 112
+    },
+    {
+      "entropy": 2.5822339403001884,
+      "epoch": 7.516129032258064,
+      "grad_norm": 1.3976553678512573,
+      "learning_rate": 7.4375e-06,
+      "loss": 3.3133,
+      "mean_token_accuracy": 0.5055951774120331,
+      "num_tokens": 161826.0,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_entropy": 2.662975311279297,
+      "eval_loss": 3.109734296798706,
+      "eval_mean_token_accuracy": 0.5159200259617397,
+      "eval_num_tokens": 172216.0,
+      "eval_runtime": 0.9281,
+      "eval_samples_per_second": 59.26,
+      "eval_steps_per_second": 15.084,
+      "step": 128
+    },
+    {
+      "entropy": 2.563361422011727,
+      "epoch": 8.129032258064516,
+      "grad_norm": 1.7696324586868286,
+      "learning_rate": 8.062500000000001e-06,
+      "loss": 3.1155,
+      "mean_token_accuracy": 0.5187091541133428,
+      "num_tokens": 175017.0,
+      "step": 130
+    },
+    {
+      "entropy": 2.588775309920311,
+      "epoch": 8.774193548387096,
+      "grad_norm": 2.261418342590332,
+      "learning_rate": 8.6875e-06,
+      "loss": 2.8235,
+      "mean_token_accuracy": 0.5475961033254861,
+      "num_tokens": 188936.0,
+      "step": 140
+    },
+    {
+      "epoch": 9.0,
+      "eval_entropy": 2.5937297514506747,
+      "eval_loss": 2.6096889972686768,
+      "eval_mean_token_accuracy": 0.5660783967801503,
+      "eval_num_tokens": 193743.0,
+      "eval_runtime": 0.9053,
+      "eval_samples_per_second": 60.757,
+      "eval_steps_per_second": 15.465,
+      "step": 144
+    },
+    {
+      "entropy": 2.5060042989881417,
+      "epoch": 9.387096774193548,
+      "grad_norm": 1.5702177286148071,
+      "learning_rate": 9.312500000000001e-06,
+      "loss": 2.5439,
+      "mean_token_accuracy": 0.5805619108049493,
+      "num_tokens": 202001.0,
+      "step": 150
+    },
+    {
+      "entropy": 2.201874099279705,
+      "epoch": 10.0,
+      "grad_norm": 1.8405438661575317,
+      "learning_rate": 9.937500000000001e-06,
+      "loss": 2.3102,
+      "mean_token_accuracy": 0.6006814374735481,
+      "num_tokens": 215270.0,
+      "step": 160
+    },
+    {
+      "epoch": 10.0,
+      "eval_entropy": 2.1728043726512363,
+      "eval_loss": 2.3522286415100098,
+      "eval_mean_token_accuracy": 0.5939501779420036,
+      "eval_num_tokens": 215270.0,
+      "eval_runtime": 0.9322,
+      "eval_samples_per_second": 58.999,
+      "eval_steps_per_second": 15.018,
+      "step": 160
+    },
+    {
+      "entropy": 2.1090281650424005,
+      "epoch": 10.64516129032258,
+      "grad_norm": 1.3122938871383667,
+      "learning_rate": 1.0562500000000001e-05,
+      "loss": 2.2236,
+      "mean_token_accuracy": 0.605573232471943,
+      "num_tokens": 229135.0,
+      "step": 170
+    },
+    {
+      "epoch": 11.0,
+      "eval_entropy": 2.126331014292581,
+      "eval_loss": 2.2020554542541504,
+      "eval_mean_token_accuracy": 0.6053547646318164,
+      "eval_num_tokens": 236797.0,
+      "eval_runtime": 0.9054,
+      "eval_samples_per_second": 60.745,
+      "eval_steps_per_second": 15.462,
+      "step": 176
+    },
+    {
+      "entropy": 2.053142737401159,
+      "epoch": 11.258064516129032,
+      "grad_norm": 1.5178934335708618,
+      "learning_rate": 1.1187500000000001e-05,
+      "loss": 2.0915,
+      "mean_token_accuracy": 0.61878864937707,
+      "num_tokens": 242377.0,
+      "step": 180
+    },
+    {
+      "entropy": 2.013620141148567,
+      "epoch": 11.903225806451612,
+      "grad_norm": 1.4182125329971313,
+      "learning_rate": 1.1812499999999999e-05,
+      "loss": 2.0478,
+      "mean_token_accuracy": 0.6269605554640293,
+      "num_tokens": 256298.0,
+      "step": 190
+    },
+    {
+      "epoch": 12.0,
+      "eval_entropy": 2.0988540819713046,
+      "eval_loss": 2.093829393386841,
+      "eval_mean_token_accuracy": 0.6164226361683437,
+      "eval_num_tokens": 258324.0,
+      "eval_runtime": 0.9948,
+      "eval_samples_per_second": 55.289,
+      "eval_steps_per_second": 14.074,
+      "step": 192
+    },
+    {
+      "entropy": 1.9682148710677498,
+      "epoch": 12.516129032258064,
+      "grad_norm": 1.3009895086288452,
+      "learning_rate": 1.24375e-05,
+      "loss": 1.9508,
+      "mean_token_accuracy": 0.6344620632497888,
+      "num_tokens": 269514.0,
+      "step": 200
+    },
+    {
+      "epoch": 13.0,
+      "eval_entropy": 2.022765415055411,
+      "eval_loss": 1.9986889362335205,
+      "eval_mean_token_accuracy": 0.6248509841305869,
+      "eval_num_tokens": 279851.0,
+      "eval_runtime": 1.3989,
+      "eval_samples_per_second": 39.316,
+      "eval_steps_per_second": 10.008,
+      "step": 208
+    },
+    {
+      "entropy": 1.9475462483732324,
+      "epoch": 13.129032258064516,
+      "grad_norm": 1.2914632558822632,
+      "learning_rate": 1.3062499999999999e-05,
+      "loss": 1.9446,
+      "mean_token_accuracy": 0.6389191699655432,
+      "num_tokens": 282652.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.9222171217203141,
+      "epoch": 13.774193548387096,
+      "grad_norm": 1.631095290184021,
+      "learning_rate": 1.36875e-05,
+      "loss": 1.8472,
+      "mean_token_accuracy": 0.6466637052595615,
+      "num_tokens": 296522.0,
+      "step": 220
+    },
+    {
+      "epoch": 14.0,
+      "eval_entropy": 1.9563691530908858,
+      "eval_loss": 1.9220991134643555,
+      "eval_mean_token_accuracy": 0.6309446564742497,
+      "eval_num_tokens": 301378.0,
+      "eval_runtime": 1.0668,
+      "eval_samples_per_second": 51.555,
+      "eval_steps_per_second": 13.123,
+      "step": 224
+    },
+    {
+      "entropy": 1.870294423479783,
+      "epoch": 14.387096774193548,
+      "grad_norm": 1.3715276718139648,
+      "learning_rate": 1.43125e-05,
+      "loss": 1.7688,
+      "mean_token_accuracy": 0.6547230929136276,
+      "num_tokens": 309834.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.8683158645504399,
+      "epoch": 15.0,
+      "grad_norm": 1.9479233026504517,
+      "learning_rate": 1.4937500000000002e-05,
+      "loss": 1.7425,
+      "mean_token_accuracy": 0.6565716470542707,
+      "num_tokens": 322905.0,
+      "step": 240
+    },
+    {
+      "epoch": 15.0,
+      "eval_entropy": 1.9176117862973894,
+      "eval_loss": 1.8483814001083374,
+      "eval_mean_token_accuracy": 0.6409520549433572,
+      "eval_num_tokens": 322905.0,
+      "eval_runtime": 0.9202,
+      "eval_samples_per_second": 59.77,
+      "eval_steps_per_second": 15.214,
+      "step": 240
+    },
+    {
+      "entropy": 1.8178010761737824,
+      "epoch": 15.64516129032258,
+      "grad_norm": 1.6151540279388428,
+      "learning_rate": 1.5562500000000002e-05,
+      "loss": 1.6598,
+      "mean_token_accuracy": 0.6694157928228378,
+      "num_tokens": 336780.0,
+      "step": 250
+    },
+    {
+      "epoch": 16.0,
+      "eval_entropy": 1.8427454914365495,
+      "eval_loss": 1.7848949432373047,
+      "eval_mean_token_accuracy": 0.6483822464942932,
+      "eval_num_tokens": 344432.0,
+      "eval_runtime": 0.8965,
+      "eval_samples_per_second": 61.351,
+      "eval_steps_per_second": 15.617,
+      "step": 256
+    },
+    {
+      "entropy": 1.7828364309511686,
+      "epoch": 16.258064516129032,
+      "grad_norm": 1.4990966320037842,
+      "learning_rate": 1.61875e-05,
+      "loss": 1.5925,
+      "mean_token_accuracy": 0.6848364127309698,
+      "num_tokens": 349950.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.7749755203723907,
+      "epoch": 16.903225806451612,
+      "grad_norm": 1.6659446954727173,
+      "learning_rate": 1.6812500000000002e-05,
+      "loss": 1.5674,
+      "mean_token_accuracy": 0.7018352136015892,
+      "num_tokens": 363887.0,
+      "step": 270
+    },
+    {
+      "epoch": 17.0,
+      "eval_entropy": 1.7996527978352137,
+      "eval_loss": 1.7261488437652588,
+      "eval_mean_token_accuracy": 0.6748419829777309,
+      "eval_num_tokens": 365959.0,
+      "eval_runtime": 0.956,
+      "eval_samples_per_second": 57.533,
+      "eval_steps_per_second": 14.645,
+      "step": 272
+    },
+    {
+      "entropy": 1.7126218849106838,
+      "epoch": 17.516129032258064,
+      "grad_norm": 1.7774029970169067,
+      "learning_rate": 1.74375e-05,
+      "loss": 1.4737,
+      "mean_token_accuracy": 0.7113534455236635,
+      "num_tokens": 377051.0,
+      "step": 280
+    },
+    {
+      "epoch": 18.0,
+      "eval_entropy": 1.7618773494447981,
+      "eval_loss": 1.6715681552886963,
+      "eval_mean_token_accuracy": 0.6734440326690674,
+      "eval_num_tokens": 387486.0,
+      "eval_runtime": 1.3598,
+      "eval_samples_per_second": 40.446,
+      "eval_steps_per_second": 10.295,
+      "step": 288
+    },
+    {
+      "entropy": 1.684084642874567,
+      "epoch": 18.129032258064516,
+      "grad_norm": 1.8488755226135254,
+      "learning_rate": 1.8062500000000002e-05,
+      "loss": 1.4353,
+      "mean_token_accuracy": 0.717556736186931,
+      "num_tokens": 390288.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.6123981848359108,
+      "epoch": 18.774193548387096,
+      "grad_norm": 1.94077467918396,
+      "learning_rate": 1.8687500000000004e-05,
+      "loss": 1.347,
+      "mean_token_accuracy": 0.7245998069643974,
+      "num_tokens": 404246.0,
+      "step": 300
+    },
+    {
+      "epoch": 19.0,
+      "eval_entropy": 1.6447282092911857,
+      "eval_loss": 1.6219120025634766,
+      "eval_mean_token_accuracy": 0.6779105194977352,
+      "eval_num_tokens": 409013.0,
+      "eval_runtime": 0.9117,
+      "eval_samples_per_second": 60.326,
+      "eval_steps_per_second": 15.356,
+      "step": 304
+    },
+    {
+      "entropy": 1.5541185391576666,
+      "epoch": 19.387096774193548,
+      "grad_norm": 2.0378854274749756,
+      "learning_rate": 1.93125e-05,
+      "loss": 1.2785,
+      "mean_token_accuracy": 0.7347154123218436,
+      "num_tokens": 417317.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.403356123911707,
+      "epoch": 20.0,
+      "grad_norm": 2.347236394882202,
+      "learning_rate": 1.99375e-05,
+      "loss": 1.219,
+      "mean_token_accuracy": 0.7410024349626742,
+      "num_tokens": 430540.0,
+      "step": 320
+    },
+    {
+      "epoch": 20.0,
+      "eval_entropy": 1.4916774034500122,
+      "eval_loss": 1.587111473083496,
+      "eval_mean_token_accuracy": 0.6795690613133567,
+      "eval_num_tokens": 430540.0,
+      "eval_runtime": 0.9048,
+      "eval_samples_per_second": 60.786,
+      "eval_steps_per_second": 15.473,
+      "step": 320
+    },
+    {
+      "entropy": 1.338417048752308,
+      "epoch": 20.64516129032258,
+      "grad_norm": 2.188633441925049,
+      "learning_rate": 2.0562500000000002e-05,
+      "loss": 1.1363,
+      "mean_token_accuracy": 0.7564118377864361,
+      "num_tokens": 444500.0,
+      "step": 330
+    },
+    {
+      "epoch": 21.0,
+      "eval_entropy": 1.3439774853842599,
+      "eval_loss": 1.5705065727233887,
+      "eval_mean_token_accuracy": 0.6734923720359802,
+      "eval_num_tokens": 452067.0,
+      "eval_runtime": 1.3705,
+      "eval_samples_per_second": 40.131,
+      "eval_steps_per_second": 10.215,
+      "step": 336
+    },
+    {
+      "entropy": 1.2597325475592362,
+      "epoch": 21.258064516129032,
+      "grad_norm": 2.0218992233276367,
+      "learning_rate": 2.1187500000000003e-05,
+      "loss": 1.0859,
+      "mean_token_accuracy": 0.7610587077705484,
+      "num_tokens": 457711.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.1984408333897592,
+      "epoch": 21.903225806451612,
+      "grad_norm": 2.203165292739868,
+      "learning_rate": 2.18125e-05,
+      "loss": 1.0145,
+      "mean_token_accuracy": 0.7772165350615978,
+      "num_tokens": 471531.0,
+      "step": 350
+    },
+    {
+      "epoch": 22.0,
+      "eval_entropy": 1.2664960197040014,
+      "eval_loss": 1.5587613582611084,
+      "eval_mean_token_accuracy": 0.6787797468049186,
+      "eval_num_tokens": 473594.0,
+      "eval_runtime": 0.9351,
+      "eval_samples_per_second": 58.82,
+      "eval_steps_per_second": 14.972,
+      "step": 352
+    },
+    {
+      "entropy": 1.1226187560119127,
+      "epoch": 22.516129032258064,
+      "grad_norm": 2.4278323650360107,
+      "learning_rate": 2.24375e-05,
+      "loss": 0.9255,
+      "mean_token_accuracy": 0.7932525535947398,
+      "num_tokens": 484678.0,
+      "step": 360
+    },
+    {
+      "epoch": 23.0,
+      "eval_entropy": 1.2237448862620763,
+      "eval_loss": 1.579514741897583,
+      "eval_mean_token_accuracy": 0.6716454710279193,
+      "eval_num_tokens": 495121.0,
+      "eval_runtime": 1.3763,
+      "eval_samples_per_second": 39.963,
+      "eval_steps_per_second": 10.172,
+      "step": 368
+    },
+    {
+      "entropy": 1.0918044400842566,
+      "epoch": 23.129032258064516,
+      "grad_norm": 2.5345664024353027,
+      "learning_rate": 2.30625e-05,
+      "loss": 0.8737,
+      "mean_token_accuracy": 0.7978831976652145,
+      "num_tokens": 497974.0,
+      "step": 370
+    },
+    {
+      "entropy": 1.006336173415184,
+      "epoch": 23.774193548387096,
+      "grad_norm": 2.779085874557495,
+      "learning_rate": 2.36875e-05,
+      "loss": 0.7646,
+      "mean_token_accuracy": 0.8216063916683197,
+      "num_tokens": 511856.0,
+      "step": 380
+    },
+    {
+      "epoch": 24.0,
+      "eval_entropy": 1.1918106589998518,
+      "eval_loss": 1.5942119359970093,
+      "eval_mean_token_accuracy": 0.6677229617323194,
+      "eval_num_tokens": 516648.0,
+      "eval_runtime": 0.9097,
+      "eval_samples_per_second": 60.46,
+      "eval_steps_per_second": 15.39,
+      "step": 384
+    },
+    {
+      "entropy": 1.0034341443526118,
+      "epoch": 24.387096774193548,
+      "grad_norm": 2.9064760208129883,
+      "learning_rate": 2.43125e-05,
+      "loss": 0.7059,
+      "mean_token_accuracy": 0.8363859167224482,
+      "num_tokens": 524969.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.9153783635089272,
+      "epoch": 25.0,
+      "grad_norm": 3.5367863178253174,
+      "learning_rate": 2.4937500000000003e-05,
+      "loss": 0.6268,
+      "mean_token_accuracy": 0.8444738458645972,
+      "num_tokens": 538175.0,
+      "step": 400
+    },
+    {
+      "epoch": 25.0,
+      "eval_entropy": 1.1169007931436812,
+      "eval_loss": 1.666494369506836,
+      "eval_mean_token_accuracy": 0.6655990694250379,
+      "eval_num_tokens": 538175.0,
+      "eval_runtime": 0.9258,
+      "eval_samples_per_second": 59.408,
+      "eval_steps_per_second": 15.122,
+      "step": 400
+    },
+    {
+      "entropy": 0.8221864104270935,
+      "epoch": 25.64516129032258,
+      "grad_norm": 2.6190507411956787,
+      "learning_rate": 2.55625e-05,
+      "loss": 0.5171,
+      "mean_token_accuracy": 0.8675303012132645,
+      "num_tokens": 552002.0,
+      "step": 410
+    },
+    {
+      "epoch": 26.0,
+      "eval_entropy": 1.0611292464392525,
+      "eval_loss": 1.6921919584274292,
+      "eval_mean_token_accuracy": 0.65951726266316,
+      "eval_num_tokens": 559702.0,
+      "eval_runtime": 1.0329,
+      "eval_samples_per_second": 53.25,
+      "eval_steps_per_second": 13.555,
+      "step": 416
+    },
+    {
+      "entropy": 0.8153277470877296,
+      "epoch": 26.258064516129032,
+      "grad_norm": 2.4259774684906006,
+      "learning_rate": 2.6187500000000003e-05,
+      "loss": 0.4676,
+      "mean_token_accuracy": 0.8747850750621996,
+      "num_tokens": 565255.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.7013958178460598,
+      "epoch": 26.903225806451612,
+      "grad_norm": 2.4626195430755615,
+      "learning_rate": 2.68125e-05,
+      "loss": 0.3867,
+      "mean_token_accuracy": 0.8833703070878982,
+      "num_tokens": 579163.0,
+      "step": 430
+    },
+    {
+      "epoch": 27.0,
+      "eval_entropy": 0.9333125693457467,
+      "eval_loss": 1.7267862558364868,
+      "eval_mean_token_accuracy": 0.658582159451076,
+      "eval_num_tokens": 581229.0,
+      "eval_runtime": 0.9233,
+      "eval_samples_per_second": 59.571,
+      "eval_steps_per_second": 15.163,
+      "step": 432
+    },
+    {
+      "entropy": 0.5856798651971316,
+      "epoch": 27.516129032258064,
+      "grad_norm": 2.773681402206421,
+      "learning_rate": 2.74375e-05,
+      "loss": 0.3408,
+      "mean_token_accuracy": 0.8944279308381834,
+      "num_tokens": 592320.0,
+      "step": 440
+    },
+    {
+      "epoch": 28.0,
+      "eval_entropy": 0.831269736800875,
+      "eval_loss": 1.8276340961456299,
+      "eval_mean_token_accuracy": 0.6552059480122158,
+      "eval_num_tokens": 602756.0,
+      "eval_runtime": 0.9803,
+      "eval_samples_per_second": 56.107,
+      "eval_steps_per_second": 14.282,
+      "step": 448
+    },
+    {
+      "entropy": 0.5249183703409998,
+      "epoch": 28.129032258064516,
+      "grad_norm": 1.7010736465454102,
+      "learning_rate": 2.80625e-05,
+      "loss": 0.3165,
+      "mean_token_accuracy": 0.9029051528165215,
+      "num_tokens": 605474.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.4536327484995127,
+      "epoch": 28.774193548387096,
+      "grad_norm": 2.132962226867676,
+      "learning_rate": 2.86875e-05,
+      "loss": 0.2865,
+      "mean_token_accuracy": 0.9036249771714211,
+      "num_tokens": 619457.0,
+      "step": 460
+    },
+    {
+      "epoch": 29.0,
+      "eval_entropy": 0.7956289521285466,
+      "eval_loss": 1.9158949851989746,
+      "eval_mean_token_accuracy": 0.6526114770344326,
+      "eval_num_tokens": 624283.0,
+      "eval_runtime": 0.9267,
+      "eval_samples_per_second": 59.35,
+      "eval_steps_per_second": 15.107,
+      "step": 464
+    },
+    {
+      "entropy": 0.4277557734596102,
+      "epoch": 29.387096774193548,
+      "grad_norm": 1.9701188802719116,
+      "learning_rate": 2.9312500000000004e-05,
+      "loss": 0.2736,
+      "mean_token_accuracy": 0.9080228907497305,
+      "num_tokens": 632664.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.3978642586030458,
+      "epoch": 30.0,
+      "grad_norm": 2.9814867973327637,
+      "learning_rate": 2.9937500000000003e-05,
+      "loss": 0.2796,
+      "mean_token_accuracy": 0.9062309014169794,
+      "num_tokens": 645810.0,
+      "step": 480
+    },
+    {
+      "epoch": 30.0,
+      "eval_entropy": 0.7981852037566048,
+      "eval_loss": 2.003068447113037,
+      "eval_mean_token_accuracy": 0.6490011853831155,
+      "eval_num_tokens": 645810.0,
+      "eval_runtime": 0.9368,
+      "eval_samples_per_second": 58.708,
+      "eval_steps_per_second": 14.944,
+      "step": 480
+    },
+    {
+      "entropy": 0.37885100245475767,
+      "epoch": 30.64516129032258,
+      "grad_norm": 2.112239360809326,
+      "learning_rate": 3.05625e-05,
+      "loss": 0.2518,
+      "mean_token_accuracy": 0.9144969284534454,
+      "num_tokens": 659784.0,
+      "step": 490
+    },
+    {
+      "epoch": 31.0,
+      "eval_entropy": 0.7598817561353955,
+      "eval_loss": 2.0737624168395996,
+      "eval_mean_token_accuracy": 0.6507022082805634,
+      "eval_num_tokens": 667337.0,
+      "eval_runtime": 0.8916,
+      "eval_samples_per_second": 61.689,
+      "eval_steps_per_second": 15.703,
+      "step": 496
+    },
+    {
+      "entropy": 0.3670440645594346,
+      "epoch": 31.258064516129032,
+      "grad_norm": 1.9339967966079712,
+      "learning_rate": 3.1187500000000006e-05,
+      "loss": 0.2544,
+      "mean_token_accuracy": 0.9085111869008917,
+      "num_tokens": 672944.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.34540521949529646,
+      "epoch": 31.903225806451612,
+      "grad_norm": 2.0099146366119385,
+      "learning_rate": 3.18125e-05,
+      "loss": 0.2468,
+      "mean_token_accuracy": 0.9127625226974487,
+      "num_tokens": 686848.0,
+      "step": 510
+    },
+    {
+      "epoch": 32.0,
+      "eval_entropy": 0.6959893958909171,
+      "eval_loss": 2.104912519454956,
+      "eval_mean_token_accuracy": 0.6566033831664494,
+      "eval_num_tokens": 688864.0,
+      "eval_runtime": 1.2103,
+      "eval_samples_per_second": 45.445,
+      "eval_steps_per_second": 11.568,
+      "step": 512
+    },
+    {
+      "entropy": 0.3452399529908833,
+      "epoch": 32.516129032258064,
+      "grad_norm": 1.8694605827331543,
+      "learning_rate": 3.24375e-05,
+      "loss": 0.2461,
+      "mean_token_accuracy": 0.9124428755358646,
+      "num_tokens": 699838.0,
+      "step": 520
+    },
+    {
+      "epoch": 33.0,
+      "eval_entropy": 0.6757666979517255,
+      "eval_loss": 2.1449453830718994,
+      "eval_mean_token_accuracy": 0.6545567682811192,
+      "eval_num_tokens": 710391.0,
+      "eval_runtime": 0.912,
+      "eval_samples_per_second": 60.306,
+      "eval_steps_per_second": 15.351,
+      "step": 528
+    },
+    {
+      "entropy": 0.3346626260562947,
+      "epoch": 33.12903225806452,
+      "grad_norm": 1.2991915941238403,
+      "learning_rate": 3.3062500000000004e-05,
+      "loss": 0.2393,
+      "mean_token_accuracy": 0.9142316736673054,
+      "num_tokens": 713076.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.3058926550671458,
+      "epoch": 33.774193548387096,
+      "grad_norm": 2.250917911529541,
+      "learning_rate": 3.36875e-05,
+      "loss": 0.2366,
+      "mean_token_accuracy": 0.9110181450843811,
+      "num_tokens": 726913.0,
+      "step": 540
+    },
+    {
+      "epoch": 34.0,
+      "eval_entropy": 0.713920282466071,
+      "eval_loss": 2.044567823410034,
+      "eval_mean_token_accuracy": 0.6525738835334778,
+      "eval_num_tokens": 731918.0,
+      "eval_runtime": 0.8817,
+      "eval_samples_per_second": 62.379,
+      "eval_steps_per_second": 15.878,
+      "step": 544
+    },
+    {
+      "entropy": 0.3304567150771618,
+      "epoch": 34.38709677419355,
+      "grad_norm": 1.6248284578323364,
+      "learning_rate": 3.43125e-05,
+      "loss": 0.234,
+      "mean_token_accuracy": 0.9141417553550318,
+      "num_tokens": 740119.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.2964809501641675,
+      "epoch": 35.0,
+      "grad_norm": 2.199978828430176,
+      "learning_rate": 3.49375e-05,
+      "loss": 0.2354,
+      "mean_token_accuracy": 0.9153264400206114,
+      "num_tokens": 753445.0,
+      "step": 560
+    },
+    {
+      "epoch": 35.0,
+      "eval_entropy": 0.6718730543340955,
+      "eval_loss": 2.131523847579956,
+      "eval_mean_token_accuracy": 0.6514393900121961,
+      "eval_num_tokens": 753445.0,
+      "eval_runtime": 0.919,
+      "eval_samples_per_second": 59.849,
+      "eval_steps_per_second": 15.234,
+      "step": 560
+    },
+    {
+      "entropy": 0.29936634581536054,
+      "epoch": 35.645161290322584,
+      "grad_norm": 1.9858863353729248,
+      "learning_rate": 3.5562500000000004e-05,
+      "loss": 0.2233,
+      "mean_token_accuracy": 0.9170688688755035,
+      "num_tokens": 767352.0,
+      "step": 570
+    },
+    {
+      "epoch": 36.0,
+      "eval_entropy": 0.6986751215798515,
+      "eval_loss": 2.072589874267578,
+      "eval_mean_token_accuracy": 0.655285677739552,
+      "eval_num_tokens": 774972.0,
+      "eval_runtime": 0.9265,
+      "eval_samples_per_second": 59.365,
+      "eval_steps_per_second": 15.111,
+      "step": 576
+    },
+    {
+      "entropy": 0.30756315883052976,
+      "epoch": 36.25806451612903,
+      "grad_norm": 1.2706995010375977,
+      "learning_rate": 3.61875e-05,
+      "loss": 0.2278,
+      "mean_token_accuracy": 0.9169254663743471,
+      "num_tokens": 780722.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.2909585501998663,
+      "epoch": 36.903225806451616,
+      "grad_norm": 2.095874786376953,
+      "learning_rate": 3.68125e-05,
+      "loss": 0.2266,
+      "mean_token_accuracy": 0.9121941901743412,
+      "num_tokens": 794511.0,
+      "step": 590
+    },
+    {
+      "epoch": 37.0,
+      "eval_entropy": 0.636478283575603,
+      "eval_loss": 2.166316270828247,
+      "eval_mean_token_accuracy": 0.6568594745227269,
+      "eval_num_tokens": 796499.0,
+      "eval_runtime": 0.9013,
+      "eval_samples_per_second": 61.02,
+      "eval_steps_per_second": 15.532,
+      "step": 592
+    },
+    {
+      "entropy": 0.28608485017167895,
+      "epoch": 37.516129032258064,
+      "grad_norm": 2.4893622398376465,
+      "learning_rate": 3.74375e-05,
+      "loss": 0.218,
+      "mean_token_accuracy": 0.9165164412636506,
+      "num_tokens": 807681.0,
+      "step": 600
+    },
+    {
+      "epoch": 38.0,
+      "eval_entropy": 0.6342436969280243,
+      "eval_loss": 2.156416177749634,
+      "eval_mean_token_accuracy": 0.6568004020622799,
+      "eval_num_tokens": 818026.0,
+      "eval_runtime": 0.9354,
+      "eval_samples_per_second": 58.798,
+      "eval_steps_per_second": 14.967,
+      "step": 608
+    },
+    {
+      "entropy": 0.2943071307320344,
+      "epoch": 38.12903225806452,
+      "grad_norm": 1.960349202156067,
+      "learning_rate": 3.8062500000000004e-05,
+      "loss": 0.2245,
+      "mean_token_accuracy": 0.9143017130462747,
+      "num_tokens": 820826.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.26704031582921745,
+      "epoch": 38.774193548387096,
+      "grad_norm": 1.1493830680847168,
+      "learning_rate": 3.8687500000000005e-05,
+      "loss": 0.2165,
+      "mean_token_accuracy": 0.9143977962434292,
+      "num_tokens": 834709.0,
+      "step": 620
+    },
+    {
+      "epoch": 39.0,
+      "eval_entropy": 0.6424140781164169,
+      "eval_loss": 2.2105581760406494,
+      "eval_mean_token_accuracy": 0.6563994671617236,
+      "eval_num_tokens": 839553.0,
+      "eval_runtime": 0.9226,
+      "eval_samples_per_second": 59.612,
+      "eval_steps_per_second": 15.174,
+      "step": 624
+    },
+    {
+      "entropy": 0.27404083448805305,
+      "epoch": 39.38709677419355,
+      "grad_norm": 1.7598483562469482,
+      "learning_rate": 3.93125e-05,
+      "loss": 0.2157,
+      "mean_token_accuracy": 0.9152095623706517,
+      "num_tokens": 847976.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.2730099213750739,
+      "epoch": 40.0,
+      "grad_norm": 1.9577555656433105,
+      "learning_rate": 3.99375e-05,
+      "loss": 0.2216,
+      "mean_token_accuracy": 0.9135262981841439,
+      "num_tokens": 861080.0,
+      "step": 640
+    },
+    {
+      "epoch": 40.0,
+      "eval_entropy": 0.623557556952749,
+      "eval_loss": 2.177314043045044,
+      "eval_mean_token_accuracy": 0.6597372846943992,
+      "eval_num_tokens": 861080.0,
+      "eval_runtime": 0.9132,
+      "eval_samples_per_second": 60.227,
+      "eval_steps_per_second": 15.33,
+      "step": 640
+    },
+    {
+      "entropy": 0.26116420738399027,
+      "epoch": 40.645161290322584,
+      "grad_norm": 1.4962230920791626,
+      "learning_rate": 4.0562500000000003e-05,
+      "loss": 0.2104,
+      "mean_token_accuracy": 0.9174227572977542,
+      "num_tokens": 874945.0,
+      "step": 650
+    },
+    {
+      "epoch": 41.0,
+      "eval_entropy": 0.6280922591686249,
+      "eval_loss": 2.182685136795044,
+      "eval_mean_token_accuracy": 0.6488148740359715,
+      "eval_num_tokens": 882607.0,
+      "eval_runtime": 0.9382,
+      "eval_samples_per_second": 58.625,
+      "eval_steps_per_second": 14.923,
+      "step": 656
+    },
+    {
+      "entropy": 0.27049236548574346,
+      "epoch": 41.25806451612903,
+      "grad_norm": 1.5585705041885376,
+      "learning_rate": 4.11875e-05,
+      "loss": 0.2172,
+      "mean_token_accuracy": 0.9116643212343517,
+      "num_tokens": 888188.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.25881535150110724,
+      "epoch": 41.903225806451616,
+      "grad_norm": 1.7957926988601685,
+      "learning_rate": 4.181250000000001e-05,
+      "loss": 0.2171,
+      "mean_token_accuracy": 0.9126927703619003,
+      "num_tokens": 902034.0,
+      "step": 670
+    },
+    {
+      "epoch": 42.0,
+      "eval_entropy": 0.6354757377079555,
+      "eval_loss": 2.1949057579040527,
+      "eval_mean_token_accuracy": 0.651188816343035,
+      "eval_num_tokens": 904134.0,
+      "eval_runtime": 0.8942,
+      "eval_samples_per_second": 61.51,
+      "eval_steps_per_second": 15.657,
+      "step": 672
+    },
+    {
+      "entropy": 0.2616837781510855,
+      "epoch": 42.516129032258064,
+      "grad_norm": 1.9319422245025635,
+      "learning_rate": 4.24375e-05,
+      "loss": 0.2111,
+      "mean_token_accuracy": 0.9157685621788627,
+      "num_tokens": 915303.0,
+      "step": 680
+    },
+    {
+      "epoch": 43.0,
+      "eval_entropy": 0.615446959223066,
+      "eval_loss": 2.2043023109436035,
+      "eval_mean_token_accuracy": 0.6558100581169128,
+      "eval_num_tokens": 925661.0,
+      "eval_runtime": 0.9252,
+      "eval_samples_per_second": 59.445,
+      "eval_steps_per_second": 15.131,
+      "step": 688
+    },
+    {
+      "entropy": 0.25998294510339437,
+      "epoch": 43.12903225806452,
+      "grad_norm": 2.184018850326538,
+      "learning_rate": 4.30625e-05,
+      "loss": 0.2175,
+      "mean_token_accuracy": 0.914588484324907,
+      "num_tokens": 928440.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.25247995406389234,
+      "epoch": 43.774193548387096,
+      "grad_norm": 2.9504449367523193,
+      "learning_rate": 4.3687500000000005e-05,
+      "loss": 0.216,
+      "mean_token_accuracy": 0.9170804493129253,
+      "num_tokens": 942357.0,
+      "step": 700
+    },
+    {
+      "epoch": 44.0,
+      "eval_entropy": 0.6387277500970023,
+      "eval_loss": 2.154686212539673,
+      "eval_mean_token_accuracy": 0.6561333068779537,
+      "eval_num_tokens": 947188.0,
+      "eval_runtime": 0.912,
+      "eval_samples_per_second": 60.307,
+      "eval_steps_per_second": 15.351,
+      "step": 704
+    },
+    {
+      "entropy": 0.26556668744275447,
+      "epoch": 44.38709677419355,
+      "grad_norm": 2.3016467094421387,
+      "learning_rate": 4.43125e-05,
+      "loss": 0.2129,
+      "mean_token_accuracy": 0.9151790534195147,
+      "num_tokens": 955541.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.25153220680199173,
+      "epoch": 45.0,
+      "grad_norm": 1.5553311109542847,
+      "learning_rate": 4.49375e-05,
+      "loss": 0.2197,
+      "mean_token_accuracy": 0.912982240319252,
+      "num_tokens": 968715.0,
+      "step": 720
+    },
+    {
+      "epoch": 45.0,
+      "eval_entropy": 0.6276453903743199,
+      "eval_loss": 2.186168670654297,
+      "eval_mean_token_accuracy": 0.6584120520523616,
+      "eval_num_tokens": 968715.0,
+      "eval_runtime": 0.9005,
+      "eval_samples_per_second": 61.074,
+      "eval_steps_per_second": 15.546,
+      "step": 720
+    },
+    {
+      "entropy": 0.2620750930160284,
+      "epoch": 45.645161290322584,
+      "grad_norm": 2.157158136367798,
+      "learning_rate": 4.55625e-05,
+      "loss": 0.2042,
+      "mean_token_accuracy": 0.9174154184758663,
+      "num_tokens": 982594.0,
+      "step": 730
+    },
+    {
+      "epoch": 46.0,
+      "eval_entropy": 0.6001809579985482,
+      "eval_loss": 2.269158124923706,
+      "eval_mean_token_accuracy": 0.6551194148404258,
+      "eval_num_tokens": 990242.0,
+      "eval_runtime": 0.9149,
+      "eval_samples_per_second": 60.114,
+      "eval_steps_per_second": 15.302,
+      "step": 736
+    },
+    {
+      "entropy": 0.24646662116834991,
+      "epoch": 46.25806451612903,
+      "grad_norm": 0.8333325982093811,
+      "learning_rate": 4.61875e-05,
+      "loss": 0.2186,
+      "mean_token_accuracy": 0.9161424346660313,
+      "num_tokens": 995750.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.25320138819515703,
+      "epoch": 46.903225806451616,
+      "grad_norm": 1.5136183500289917,
+      "learning_rate": 4.6812500000000006e-05,
+      "loss": 0.212,
+      "mean_token_accuracy": 0.9146950207650661,
+      "num_tokens": 1009725.0,
+      "step": 750
+    },
+    {
+      "epoch": 47.0,
+      "eval_entropy": 0.6296457903725761,
+      "eval_loss": 2.1639528274536133,
+      "eval_mean_token_accuracy": 0.6583362604890551,
+      "eval_num_tokens": 1011769.0,
+      "eval_runtime": 0.8933,
+      "eval_samples_per_second": 61.57,
+      "eval_steps_per_second": 15.672,
+      "step": 752
+    },
+    {
+      "entropy": 0.25277749547048617,
+      "epoch": 47.516129032258064,
+      "grad_norm": 2.703397512435913,
+      "learning_rate": 4.74375e-05,
+      "loss": 0.2107,
+      "mean_token_accuracy": 0.9154670128696843,
+      "num_tokens": 1022922.0,
+      "step": 760
+    },
+    {
+      "epoch": 48.0,
+      "eval_entropy": 0.6431450226477214,
+      "eval_loss": 2.113975763320923,
+      "eval_mean_token_accuracy": 0.6571915745735168,
+      "eval_num_tokens": 1033296.0,
+      "eval_runtime": 1.4606,
+      "eval_samples_per_second": 37.656,
+      "eval_steps_per_second": 9.585,
+      "step": 768
+    },
+    {
+      "entropy": 0.2505563164227887,
+      "epoch": 48.12903225806452,
+      "grad_norm": 1.7070248126983643,
+      "learning_rate": 4.80625e-05,
+      "loss": 0.2181,
+      "mean_token_accuracy": 0.9125990342152747,
+      "num_tokens": 1036124.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.2494984647259116,
+      "epoch": 48.774193548387096,
+      "grad_norm": 2.354995012283325,
+      "learning_rate": 4.8687500000000004e-05,
+      "loss": 0.2069,
+      "mean_token_accuracy": 0.9165523618459701,
+      "num_tokens": 1050032.0,
+      "step": 780
+    },
+    {
+      "epoch": 49.0,
+      "eval_entropy": 0.603933504649571,
+      "eval_loss": 2.2200510501861572,
+      "eval_mean_token_accuracy": 0.6548148649079459,
+      "eval_num_tokens": 1054823.0,
+      "eval_runtime": 0.9123,
+      "eval_samples_per_second": 60.286,
+      "eval_steps_per_second": 15.346,
+      "step": 784
+    },
+    {
+      "entropy": 0.24296215019728007,
+      "epoch": 49.38709677419355,
+      "grad_norm": 1.5552977323532104,
+      "learning_rate": 4.93125e-05,
+      "loss": 0.2083,
+      "mean_token_accuracy": 0.9156087629104915,
+      "num_tokens": 1063159.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.24393935266293978,
+      "epoch": 50.0,
+      "grad_norm": 1.544976830482483,
+      "learning_rate": 4.99375e-05,
+      "loss": 0.2157,
+      "mean_token_accuracy": 0.9146833968789954,
+      "num_tokens": 1076350.0,
+      "step": 800
+    },
+    {
+      "epoch": 50.0,
+      "eval_entropy": 0.6158908797161919,
+      "eval_loss": 2.2002458572387695,
+      "eval_mean_token_accuracy": 0.6551659618105207,
+      "eval_num_tokens": 1076350.0,
+      "eval_runtime": 0.9028,
+      "eval_samples_per_second": 60.923,
+      "eval_steps_per_second": 15.508,
+      "step": 800
+    },
+    {
+      "entropy": 0.24434087462723256,
+      "epoch": 50.645161290322584,
+      "grad_norm": 1.5835460424423218,
+      "learning_rate": 5.05625e-05,
+      "loss": 0.2053,
+      "mean_token_accuracy": 0.9157114021480084,
+      "num_tokens": 1090170.0,
+      "step": 810
+    },
+    {
+      "epoch": 51.0,
+      "eval_entropy": 0.6001614396061216,
+      "eval_loss": 2.134579658508301,
+      "eval_mean_token_accuracy": 0.6620945462158748,
+      "eval_num_tokens": 1097877.0,
+      "eval_runtime": 0.9182,
+      "eval_samples_per_second": 59.901,
+      "eval_steps_per_second": 15.248,
+      "step": 816
+    },
+    {
+      "entropy": 0.2386562437995484,
+      "epoch": 51.25806451612903,
+      "grad_norm": 0.8457896709442139,
+      "learning_rate": 5.11875e-05,
+      "loss": 0.2112,
+      "mean_token_accuracy": 0.9135481056414152,
+      "num_tokens": 1103447.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.23914105109870434,
+      "epoch": 51.903225806451616,
+      "grad_norm": 1.2757948637008667,
+      "learning_rate": 5.18125e-05,
+      "loss": 0.2121,
+      "mean_token_accuracy": 0.917195787280798,
+      "num_tokens": 1117426.0,
+      "step": 830
+    },
+    {
+      "epoch": 52.0,
+      "eval_entropy": 0.6030709551913398,
+      "eval_loss": 2.1421921253204346,
+      "eval_mean_token_accuracy": 0.6576450892857143,
+      "eval_num_tokens": 1119404.0,
+      "eval_runtime": 0.9157,
+      "eval_samples_per_second": 60.065,
+      "eval_steps_per_second": 15.289,
+      "step": 832
+    },
+    {
+      "entropy": 0.23953668361431674,
+      "epoch": 52.516129032258064,
+      "grad_norm": 0.7424585223197937,
+      "learning_rate": 5.243750000000001e-05,
+      "loss": 0.206,
+      "mean_token_accuracy": 0.9173323300323988,
+      "num_tokens": 1130592.0,
+      "step": 840
+    },
+    {
+      "epoch": 53.0,
+      "eval_entropy": 0.6143183495317187,
+      "eval_loss": 2.136685609817505,
+      "eval_mean_token_accuracy": 0.661886956010546,
+      "eval_num_tokens": 1140931.0,
+      "eval_runtime": 0.9082,
+      "eval_samples_per_second": 60.559,
+      "eval_steps_per_second": 15.415,
+      "step": 848
+    },
+    {
+      "entropy": 0.24182377598787608,
+      "epoch": 53.12903225806452,
+      "grad_norm": 1.3732322454452515,
+      "learning_rate": 5.30625e-05,
+      "loss": 0.2121,
+      "mean_token_accuracy": 0.9144565549335981,
+      "num_tokens": 1143685.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.22879959754645823,
+      "epoch": 53.774193548387096,
+      "grad_norm": 2.147244453430176,
+      "learning_rate": 5.3687500000000004e-05,
+      "loss": 0.2054,
+      "mean_token_accuracy": 0.9151782430708408,
+      "num_tokens": 1157611.0,
+      "step": 860
+    },
+    {
+      "epoch": 54.0,
+      "eval_entropy": 0.6321406619889396,
+      "eval_loss": 2.204887628555298,
+      "eval_mean_token_accuracy": 0.6532182906355176,
+      "eval_num_tokens": 1162458.0,
+      "eval_runtime": 0.9208,
+      "eval_samples_per_second": 59.732,
+      "eval_steps_per_second": 15.205,
+      "step": 864
+    },
+    {
+      "entropy": 0.23761214551172757,
+      "epoch": 54.38709677419355,
+      "grad_norm": 1.3003839254379272,
+      "learning_rate": 5.43125e-05,
+      "loss": 0.2035,
+      "mean_token_accuracy": 0.9193885200902036,
+      "num_tokens": 1170903.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.2340365965899668,
+      "epoch": 55.0,
+      "grad_norm": 2.1319892406463623,
+      "learning_rate": 5.49375e-05,
+      "loss": 0.2094,
+      "mean_token_accuracy": 0.9123364067391345,
+      "num_tokens": 1183985.0,
+      "step": 880
+    },
+    {
+      "epoch": 55.0,
+      "eval_entropy": 0.5765226589781898,
+      "eval_loss": 2.259164333343506,
+      "eval_mean_token_accuracy": 0.6540640251977103,
+      "eval_num_tokens": 1183985.0,
+      "eval_runtime": 1.3389,
+      "eval_samples_per_second": 41.077,
+      "eval_steps_per_second": 10.456,
+      "step": 880
+    },
+    {
+      "entropy": 0.22173939775675536,
+      "epoch": 55.645161290322584,
+      "grad_norm": 0.9774155616760254,
+      "learning_rate": 5.556250000000001e-05,
+      "loss": 0.2028,
+      "mean_token_accuracy": 0.9162920407950879,
+      "num_tokens": 1197803.0,
+      "step": 890
+    },
+    {
+      "epoch": 56.0,
+      "eval_entropy": 0.6301779236112323,
+      "eval_loss": 2.164349317550659,
+      "eval_mean_token_accuracy": 0.6591020779950278,
+      "eval_num_tokens": 1205512.0,
+      "eval_runtime": 0.8858,
+      "eval_samples_per_second": 62.094,
+      "eval_steps_per_second": 15.806,
+      "step": 896
+    },
+    {
+      "entropy": 0.24067558975596176,
+      "epoch": 56.25806451612903,
+      "grad_norm": 0.6777637004852295,
+      "learning_rate": 5.6187500000000004e-05,
+      "loss": 0.2047,
+      "mean_token_accuracy": 0.9156502038240433,
+      "num_tokens": 1211040.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.22286444082856177,
+      "epoch": 56.903225806451616,
+      "grad_norm": 1.1683127880096436,
+      "learning_rate": 5.68125e-05,
+      "loss": 0.2092,
+      "mean_token_accuracy": 0.9164877288043499,
+      "num_tokens": 1224951.0,
+      "step": 910
+    },
+    {
+      "epoch": 57.0,
+      "eval_entropy": 0.6137891731091908,
+      "eval_loss": 2.166926622390747,
+      "eval_mean_token_accuracy": 0.655881038733891,
+      "eval_num_tokens": 1227039.0,
+      "eval_runtime": 0.9144,
+      "eval_samples_per_second": 60.149,
+      "eval_steps_per_second": 15.311,
+      "step": 912
+    },
+    {
+      "entropy": 0.22742715889686033,
+      "epoch": 57.516129032258064,
+      "grad_norm": 1.949874997138977,
+      "learning_rate": 5.74375e-05,
+      "loss": 0.1963,
+      "mean_token_accuracy": 0.9188078069373181,
+      "num_tokens": 1238175.0,
+      "step": 920
+    },
+    {
+      "epoch": 58.0,
+      "eval_entropy": 0.6465144370283399,
+      "eval_loss": 2.1403896808624268,
+      "eval_mean_token_accuracy": 0.6535507994038718,
+      "eval_num_tokens": 1248566.0,
+      "eval_runtime": 0.9857,
+      "eval_samples_per_second": 55.798,
+      "eval_steps_per_second": 14.203,
+      "step": 928
+    },
+    {
+      "entropy": 0.2348696542413611,
+      "epoch": 58.12903225806452,
+      "grad_norm": 0.7200958728790283,
+      "learning_rate": 5.8062499999999995e-05,
+      "loss": 0.2062,
+      "mean_token_accuracy": 0.9138364462476027,
+      "num_tokens": 1251370.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.23166095688939095,
+      "epoch": 58.774193548387096,
+      "grad_norm": 2.3401575088500977,
+      "learning_rate": 5.8687500000000003e-05,
+      "loss": 0.2022,
+      "mean_token_accuracy": 0.9133141487836838,
+      "num_tokens": 1265252.0,
+      "step": 940
+    },
+    {
+      "epoch": 59.0,
+      "eval_entropy": 0.5926203238112586,
+      "eval_loss": 2.1573755741119385,
+      "eval_mean_token_accuracy": 0.6642243266105652,
+      "eval_num_tokens": 1270093.0,
+      "eval_runtime": 1.3512,
+      "eval_samples_per_second": 40.706,
+      "eval_steps_per_second": 10.362,
+      "step": 944
+    },
+    {
+      "entropy": 0.228854532304563,
+      "epoch": 59.38709677419355,
+      "grad_norm": 1.2065060138702393,
+      "learning_rate": 5.9312500000000005e-05,
+      "loss": 0.204,
+      "mean_token_accuracy": 0.915436535289413,
+      "num_tokens": 1278422.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.2283171534930405,
+      "epoch": 60.0,
+      "grad_norm": 1.6328575611114502,
+      "learning_rate": 5.99375e-05,
+      "loss": 0.2106,
+      "mean_token_accuracy": 0.9148200319001549,
+      "num_tokens": 1291620.0,
+      "step": 960
+    },
+    {
+      "epoch": 60.0,
+      "eval_entropy": 0.6066372990608215,
+      "eval_loss": 2.2142343521118164,
+      "eval_mean_token_accuracy": 0.663521830524717,
+      "eval_num_tokens": 1291620.0,
+      "eval_runtime": 0.918,
+      "eval_samples_per_second": 59.916,
+      "eval_steps_per_second": 15.251,
+      "step": 960
+    },
+    {
+      "entropy": 0.22587883714586496,
+      "epoch": 60.645161290322584,
+      "grad_norm": 1.1729897260665894,
+      "learning_rate": 6.05625e-05,
+      "loss": 0.2004,
+      "mean_token_accuracy": 0.918365728110075,
+      "num_tokens": 1305660.0,
+      "step": 970
+    },
+    {
+      "epoch": 61.0,
+      "eval_entropy": 0.6117608717509678,
+      "eval_loss": 2.096813678741455,
+      "eval_mean_token_accuracy": 0.6604258716106415,
+      "eval_num_tokens": 1313147.0,
+      "eval_runtime": 0.9077,
+      "eval_samples_per_second": 60.594,
+      "eval_steps_per_second": 15.424,
+      "step": 976
+    },
+    {
+      "entropy": 0.23531277536561615,
+      "epoch": 61.25806451612903,
+      "grad_norm": 0.6755152344703674,
+      "learning_rate": 6.11875e-05,
+      "loss": 0.2082,
+      "mean_token_accuracy": 0.9143172777012775,
+      "num_tokens": 1318734.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.2311376605182886,
+      "epoch": 61.903225806451616,
+      "grad_norm": 1.2641390562057495,
+      "learning_rate": 6.18125e-05,
+      "loss": 0.2046,
+      "mean_token_accuracy": 0.9152424365282059,
+      "num_tokens": 1332705.0,
+      "step": 990
+    },
+    {
+      "epoch": 62.0,
+      "eval_entropy": 0.614239479814257,
+      "eval_loss": 2.1853811740875244,
+      "eval_mean_token_accuracy": 0.6579888761043549,
+      "eval_num_tokens": 1334674.0,
+      "eval_runtime": 0.912,
+      "eval_samples_per_second": 60.308,
+      "eval_steps_per_second": 15.351,
+      "step": 992
+    },
+    {
+      "entropy": 0.22623609006404877,
+      "epoch": 62.516129032258064,
+      "grad_norm": 0.73882657289505,
+      "learning_rate": 6.24375e-05,
+      "loss": 0.196,
+      "mean_token_accuracy": 0.9183140248060226,
+      "num_tokens": 1345954.0,
+      "step": 1000
+    },
+    {
+      "epoch": 63.0,
+      "eval_entropy": 0.5942062480109078,
+      "eval_loss": 2.2710092067718506,
+      "eval_mean_token_accuracy": 0.6534528051103864,
+      "eval_num_tokens": 1356201.0,
+      "eval_runtime": 0.9816,
+      "eval_samples_per_second": 56.034,
+      "eval_steps_per_second": 14.263,
+      "step": 1008
+    },
+    {
+      "entropy": 0.23058188216466652,
+      "epoch": 63.12903225806452,
+      "grad_norm": 1.617550253868103,
+      "learning_rate": 6.306250000000001e-05,
+      "loss": 0.2061,
+      "mean_token_accuracy": 0.9149901968868155,
+      "num_tokens": 1358961.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.2263046816922724,
+      "epoch": 63.774193548387096,
+      "grad_norm": 1.7583829164505005,
+      "learning_rate": 6.36875e-05,
+      "loss": 0.1997,
+      "mean_token_accuracy": 0.9183584488928318,
+      "num_tokens": 1372891.0,
+      "step": 1020
+    },
+    {
+      "epoch": 64.0,
+      "eval_entropy": 0.5932143756321498,
+      "eval_loss": 2.1655139923095703,
+      "eval_mean_token_accuracy": 0.659838148525783,
+      "eval_num_tokens": 1377728.0,
+      "eval_runtime": 0.8899,
+      "eval_samples_per_second": 61.807,
+      "eval_steps_per_second": 15.733,
+      "step": 1024
+    },
+    {
+      "entropy": 0.23112847656011581,
+      "epoch": 64.38709677419355,
+      "grad_norm": 1.0555381774902344,
+      "learning_rate": 6.43125e-05,
+      "loss": 0.2039,
+      "mean_token_accuracy": 0.9167588760978297,
+      "num_tokens": 1386057.0,
+      "step": 1030
+    },
+    {
+      "entropy": 0.22365212891446917,
+      "epoch": 65.0,
+      "grad_norm": 1.4283499717712402,
+      "learning_rate": 6.493750000000001e-05,
+      "loss": 0.2045,
+      "mean_token_accuracy": 0.9147814010318956,
+      "num_tokens": 1399255.0,
+      "step": 1040
+    },
+    {
+      "epoch": 65.0,
+      "eval_entropy": 0.5940606317349842,
+      "eval_loss": 2.169837713241577,
+      "eval_mean_token_accuracy": 0.6539296635559627,
+      "eval_num_tokens": 1399255.0,
+      "eval_runtime": 0.9164,
+      "eval_samples_per_second": 60.019,
+      "eval_steps_per_second": 15.277,
+      "step": 1040
+    },
+    {
+      "entropy": 0.23262295462191104,
+      "epoch": 65.64516129032258,
+      "grad_norm": 1.1094037294387817,
+      "learning_rate": 6.55625e-05,
+      "loss": 0.1981,
+      "mean_token_accuracy": 0.9165611855685711,
+      "num_tokens": 1413210.0,
+      "step": 1050
+    },
+    {
+      "epoch": 66.0,
+      "eval_entropy": 0.6009477249213627,
+      "eval_loss": 2.1785833835601807,
+      "eval_mean_token_accuracy": 0.660406789609364,
+      "eval_num_tokens": 1420782.0,
+      "eval_runtime": 0.8936,
+      "eval_samples_per_second": 61.552,
+      "eval_steps_per_second": 15.668,
+      "step": 1056
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 16000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1000,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.976888600434278e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10608/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10608/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-10608/chat_template.jinja

@@ -0,0 +1,186 @@
+{{ bos_token }}{% if documents %}
+{% set tools = [] %}
+{%- macro document_turn(documents) -%}
+{# format documents into chat turn #}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_THINKING|>I will look through the document to address the users needs.<|END_THINKING|><|START_ACTION|>[
+    {"tool_call_id": "0", "tool_name": "direct-injected-document", "parameters": {}}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+    {
+        "tool_call_id": "0",
+        "results": {
+{% for doc in documents %}
+            "{{ loop.index0 }}": {{doc|tojson}}{% if not loop.last %},
+            {% endif %}
+{% endfor %}
+
+        },
+        "is_error": null
+    }
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>{%- endmacro %}
+{%- macro tool_call_id_to_int(messages, tool_call_id) %}
+{%- set counter = namespace(value=0) %}
+{%- set tool_call_id_seen = namespace(value=false) %}
+{%- for msg in messages %}
+    {%- if msg.tool_calls %}
+        {%- for tool_call in msg.tool_calls %}
+            {%- if tool_call.id == tool_call_id and not tool_call_id_seen.value -%}
+                {{ counter.value }}
+                {%- set tool_call_id_seen.value = true %}
+            {%- endif %}
+            {%- set counter.value = counter.value + 1 %}
+        {%- endfor %}
+    {%- endif %}
+{%- endfor %}
+{%- endmacro %}
+{%- macro format_tool_message(messages, tool_msg) -%}
+{# format tool message #}
+    {
+        "tool_call_id": "{{ tool_call_id_to_int(messages, tool_msg.tool_call_id) }}",
+        "results": {
+            "0": {{ tool_msg.content|tojson }}
+        },
+        "is_error": null
+    }
+{%- endmacro -%}
+{%- if messages and messages[0]['role']|lower == 'system' %}{%- set developer_preamble = messages[0]['content'] %}{% endif %}
+{%- set tool_idx = namespace(value=0) %}
+{%- set tool_ids_seen = namespace(value=[]) %}
+{%- set sent_documents = namespace(value=false) %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
+You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
+
+Your information cutoff date is June 2024.
+
+You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
+{% if tools or documents %}
+
+You have been trained to have advanced reasoning and tool-use capabilities and you should make best use of these skills to serve user's requests.
+
+## Tool Use
+Think about how you can make best use of the provided tools to help with the task and come up with a high level plan that you will execute first.
+
+0. Start by writing <|START_THINKING|> followed by a detailed step by step plan of how you will solve the problem. For each step explain your thinking fully and give details of required tool calls (if needed). Unless specified otherwise, you write your plan in natural language. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when the user request is so straightforward to address that only a trivial plan would be needed.
+    NOTE: You MUST skip this step when you are directly responding to the user's request without using any tools.
+
+Then carry out your plan by repeatedly executing the following steps.
+1. Action: write <|START_ACTION|> followed by a list of JSON-formatted tool calls, with each one containing "tool_name" and "parameters" fields.
+    When there are multiple tool calls which are completely independent of each other (i.e. they can be executed in parallel), you should list them out all together in one step. When you finish, close it out with <|END_ACTION|>.
+2. Observation: you will then receive results of those tool calls in JSON format in the very next turn, wrapped around by <|START_TOOL_RESULT|> and <|END_TOOL_RESULT|>. Carefully observe those results and think about what to do next. Note that these results will be provided to you in a separate turn. NEVER hallucinate results.
+    Every tool call produces a list of results (when a tool call produces no result or a single result, it'll still get wrapped inside a list). Each result is clearly linked to its originating tool call via its "tool_call_id".
+3. Reflection: start the next turn by writing <|START_THINKING|> followed by what you've figured out so far, any changes you need to make to your plan, and what you will do next. When you finish, close it out with <|END_THINKING|>.
+    You can optionally choose to skip this step when everything is going according to plan and no special pieces of information or reasoning chains need to be recorded.
+    NOTE: You MUST skip this step when you are done with tool-use actions and are ready to respond to the user.
+
+You can repeat the above 3 steps multiple times (could be 0 times too if no suitable tool calls are available or needed), until you decide it's time to finally respond to the user.
+
+4. Response: then break out of the loop and write <|START_RESPONSE|> followed by a piece of text which serves as a response to the user's last request. Use all previous tool calls and results to help you when formulating your response. When you finish, close it out with <|END_RESPONSE|>.
+{% if enable_citations %}
+
+## Grounding
+Importantly, note that "Reflection" and "Response" above can be grounded.
+Grounding means you associate pieces of texts (called "spans") with those specific tool results that support them (called "sources"). And you use a pair of tags "<co>" and "</co>" to indicate when a span can be grounded onto a list of sources, listing them out in the closing tag. Sources from the same tool call are grouped together and listed as "{tool_call_id}:[{list of result indices}]", before they are joined together by ",". E.g., "<co>span</co: 0:[1,2],1:[0]>" means that "span" is supported by result 1 and 2 from "tool_call_id=0" as well as result 0 from "tool_call_id=1".
+{% endif %}
+
+## Available Tools
+Here is the list of tools that you have available to you.
+You can ONLY use the tools listed here. When a tool is not listed below, it is NOT available and you should NEVER attempt to use it.
+Each tool is represented as a JSON object with fields like "name", "description", "parameters" (per JSON Schema), and optionally, "responses" (per JSON Schema).
+
+```json
+[
+{% if documents %}
+    {"name": "direct-injected-document", "description": "This is a special tool to directly inject user-uploaded documents into the chat as additional context. DO NOT use this tool by yourself!", "parameters": {"type": "object", "properties": {}, "required": []}, "responses": {"200": {"description": "Successfully returned a list of chunked text snippets from the directly uploaded documents.", "content": {"application/json": {"schema": {"type": "array", "items": {"type": "object", "required": ["url", "snippet"], "properties": {"url": {"type": "string", "description": "The url of the uploaded document."}, "snippet": {"type": "string", "description": "The text snippet for the returned document chunk."}}}}}}}}}{%- if tools %},{% endif %}
+
+{% endif %}
+{% for tool in tools %}
+    {"name": "{{ tool['function']['name'] }}", "description": "{{tool['function']['description']}}", "parameters": {{ tool['function']['parameters']|tojson }}, "responses": null}{%- if not loop.last %},{% endif %}
+
+{% endfor %}
+]
+```
+
+{% endif %}
+# Default Preamble
+The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
+- Your name is Command.
+- You are a large language model built by Cohere.
+- You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
+- If the input is ambiguous, ask clarifying follow-up questions.
+- Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
+- Use LaTeX to generate mathematical notation for complex equations.
+- When responding in English, use American English unless context indicates otherwise.
+- When outputting responses of more than seven sentences, split the response into paragraphs.
+- Prefer the active voice.
+- Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
+- Use gender-neutral pronouns for unspecified persons.
+- Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
+- Use the third person when asked to write a summary.
+- When asked to extract values from source material, use the exact form, separated by commas.
+- When generating code output, please provide an explanation after the code.
+- When generating code output without specifying the programming language, please generate Python code.
+- If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.
+{%- if developer_preamble %}
+
+
+# Developer Preamble
+The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
+{{ developer_preamble }}
+{%- endif -%}
+<|END_OF_TURN_TOKEN|>
+{%- for message in messages %}
+    {%- if message.role|lower == 'system' and not (loop.first and developer_preamble)%}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>
+    {%- elif message.role|lower == 'user' %}
+<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{ message.content }}<|END_OF_TURN_TOKEN|>{%- if documents and not sent_documents.value %}{%- set sent_documents.value = true %}{% set tool_idx.value = tool_idx.value + 1 %}{{ document_turn(documents) }}{% endif %}
+    {%- elif message.role|lower == 'assistant' or message.role|lower == 'chatbot' %}
+<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{% if message.tool_calls %}<|START_THINKING|>{{message.tool_plan}}<|END_THINKING|><|START_ACTION|>[
+    {% for tc in message.tool_calls %}
+    {"tool_call_id": "{{ tool_idx.value }}", "tool_name": "{{ tc['function']['name'] }}", "parameters": {{ tc['function']['arguments']|tojson }}}{% if not loop.last %},{% endif %}
+
+    {% set tool_idx.value = tool_idx.value + 1 %}
+    {% endfor %}
+]<|END_ACTION|><|END_OF_TURN_TOKEN|>{% else %}<|START_RESPONSE|>{{message.content}}<|END_RESPONSE|><|END_OF_TURN_TOKEN|>{% endif %}
+    {% elif message.role|lower == 'tool' and message.tool_call_id not in tool_ids_seen.value %}
+<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|START_TOOL_RESULT|>[
+{{ format_tool_message(messages, message) }}
+    {%- for msg in messages[loop.index0 + 1:] %}
+        {%- if msg.role|lower == 'tool' %},
+{{ format_tool_message(messages, msg) }}
+            {%- set tool_ids_seen.value = tool_ids_seen.value + [msg.tool_call_id] %}
+        {%- else %}
+            {%- break %}
+        {%- endif %}
+    {%- endfor %}
+
+]<|END_TOOL_RESULT|><|END_OF_TURN_TOKEN|>
+    {%- endif %}
+{%- endfor %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+{%- else -%}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}
+    {%- set system_message = messages[0]['content'] %}{% elif false == true %}
+    {%- set loop_messages = messages %}{% set system_message = '' %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- set system_message = false %}
+{%- endif %}
+{%- if system_message != false -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}
+{%- else -%}
+    {{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><|END_OF_TURN_TOKEN|>' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif -%}
+    {%- set content = message['content'] -%}
+    {%- if message['role'] == 'user' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}
+    {%- elif message['role'] == 'assistant' -%}
+        {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>'  + content.strip() + '<|END_RESPONSE|><|END_OF_TURN_TOKEN|>' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt -%}
+    {{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>' }}
+{%- endif %}
+{% endif %}

checkpoint-10608/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10608/tokenizer_config.json

@@ -0,0 +1,353 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|START_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|END_THINKING|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|START_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255022": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255023": {
+      "content": "<|START_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|END_ACTION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|START_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|END_TOOL_RESULT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|NEW_FILE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255029": {
+      "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255030": {
+      "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255031": {
+      "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255032": {
+      "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|START_RESPONSE|>",
+    "<|END_RESPONSE|>"
+  ],
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": "<UNK>",
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}

checkpoint-10672/README.md

@@ -0,0 +1,209 @@
+---
+base_model: CohereForAI/c4ai-command-r7b-12-2024
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereForAI/c4ai-command-r7b-12-2024
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-10672/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereForAI/c4ai-command-r7b-12-2024",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}