Add files using upload-large-folder tool

README.md

@@ -1,3 +1,10 @@
+---
+tags:
+- unsloth
+base_model:
+- Qwen/Qwen3-8B
+license: apache-2.0
+---
 # Qwen3-8B
 
 ## Qwen3 Highlights
@@ -94,7 +101,7 @@ For deployment, you can use `vllm>=0.8.5` or `sglang>=0.4.5.post2` to create an
 
 > [!TIP]
 > The `enable_thinking` switch is also available in APIs created by vLLM and SGLang. 
-> Please refer to [our documentation](https://qwen.readthedocs.io/) for more details.
+> Please refer to our documentation for [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) and [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) users.
 
 ### `enable_thinking=True`
 
@@ -202,7 +209,6 @@ Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https
 
 To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
 ```python
-import os
 from qwen_agent.agents import Assistant
 
 # Define LLM
@@ -232,6 +238,10 @@ tools = [
                 'command': 'uvx',
                 'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
             },
+            "fetch": {
+                "command": "uvx",
+                "args": ["mcp-server-fetch"]
+            }
         }
     },
   'code_interpreter',  # Built-in tools
@@ -241,7 +251,7 @@ tools = [
 bot = Assistant(llm=llm_cfg, function_list=tools)
 
 # Streaming generation
-messages = [{'role': 'user', 'content': 'What time is it?'}]
+messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
 for responses in bot.run(messages=messages):
     pass
 print(responses)

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -4,7 +4,6 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -17,14 +16,16 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 36,
   "num_key_value_heads": 8,
+  "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.51.0",
+  "transformers_version": "4.52.0.dev0",
+  "unsloth_fixed": true,
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
-}
+}

generation_config.json

@@ -1,13 +1,14 @@
 {
-    "bos_token_id": 151643,
-    "do_sample": true,
-    "eos_token_id": [
-        151645,
-        151643
-    ],
-    "pad_token_id": 151643,
-    "temperature": 0.6,
-    "top_k": 20,
-    "top_p": 0.95,
-    "transformers_version": "4.51.0"
-}
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 40960,
+  "pad_token_id": 151654,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0dc64934ae0f730ddc80d99af44968d01a89e8454df07d762096ea1356446bc
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58533b468c31caa0222540a8aefddea1d74dc6e1fee928da8556d3d85729d6e
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74927fec432e050365bf757bb30348f560a44394efac89f492680b7c910b64fd
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb73f466fade5716702bda38d4e3b321c9358c39889e46fb9d613fb038bfcb2f
+size 1580230264

model.safetensors.index.json

@@ -3,404 +3,404 @@
     "total_size": 16381470720
   },
   "weight_map": {
-    "lm_head.weight": "model-00005-of-00005.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
-    "model.norm.weight": "model-00004-of-00005.safetensors"
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
   }
 }

special_tokens_map.json

@@ -22,7 +22,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "<|vision_pad|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -227,12 +227,13 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 131072,
-  "pad_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null