Instructions to use PatrickHaller/gdn-midtraining-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PatrickHaller/gdn-midtraining-sft with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="PatrickHaller/gdn-midtraining-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("PatrickHaller/gdn-midtraining-sft", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PatrickHaller/gdn-midtraining-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PatrickHaller/gdn-midtraining-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PatrickHaller/gdn-midtraining-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PatrickHaller/gdn-midtraining-sft

SGLang

How to use PatrickHaller/gdn-midtraining-sft with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "PatrickHaller/gdn-midtraining-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PatrickHaller/gdn-midtraining-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "PatrickHaller/gdn-midtraining-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PatrickHaller/gdn-midtraining-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PatrickHaller/gdn-midtraining-sft with Docker Model Runner:
```
docker model run hf.co/PatrickHaller/gdn-midtraining-sft
```

PatrickHaller commited on Jan 27

Commit

1fee875

verified ·

1 Parent(s): ba36e37

Model save

Browse files

Files changed (4) hide show

all_results.json +9 -0
generation_config.json +1 -3
train_results.json +9 -0
trainer_state.json +0 -0

all_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 2.0,
+    "total_flos": 3.1404917922249834e+19,
+    "train_loss": 1.4016287254459527,
+    "train_runtime": 304386.5826,
+    "train_samples": 1092328,
+    "train_samples_per_second": 7.177,
+    "train_steps_per_second": 0.06
+}

generation_config.json CHANGED Viewed

@@ -1,9 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
-  "eos_token_id": [
-    2
-  ],
   "pad_token_id": 0,
   "transformers_version": "4.57.3"
 }

 {
   "_from_model_config": true,
   "bos_token_id": 0,
+  "eos_token_id": 2,
   "pad_token_id": 0,
   "transformers_version": "4.57.3"
 }

train_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 2.0,
+    "total_flos": 3.1404917922249834e+19,
+    "train_loss": 1.4016287254459527,
+    "train_runtime": 304386.5826,
+    "train_samples": 1092328,
+    "train_samples_per_second": 7.177,
+    "train_steps_per_second": 0.06
+}

trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff