Instructions to use Thimphou/MNLP_M3_SFT_code_10percent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Thimphou/MNLP_M3_SFT_code_10percent with Transformers:

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

pipe = pipeline("text-generation", model="Thimphou/MNLP_M3_SFT_code_10percent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Thimphou/MNLP_M3_SFT_code_10percent")
model = AutoModelForCausalLM.from_pretrained("Thimphou/MNLP_M3_SFT_code_10percent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Thimphou/MNLP_M3_SFT_code_10percent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Thimphou/MNLP_M3_SFT_code_10percent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Thimphou/MNLP_M3_SFT_code_10percent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Thimphou/MNLP_M3_SFT_code_10percent

SGLang

How to use Thimphou/MNLP_M3_SFT_code_10percent 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 "Thimphou/MNLP_M3_SFT_code_10percent" \
    --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": "Thimphou/MNLP_M3_SFT_code_10percent",
		"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 "Thimphou/MNLP_M3_SFT_code_10percent" \
        --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": "Thimphou/MNLP_M3_SFT_code_10percent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Thimphou/MNLP_M3_SFT_code_10percent with Docker Model Runner:
```
docker model run hf.co/Thimphou/MNLP_M3_SFT_code_10percent
```

Thimphou commited on Jun 5, 2025

Commit

b779dbf

verified ·

1 Parent(s): 7f57a9f

Fine-tuned Qwen model with 10.0% code feedback (seed=42, MetaMath validation)

Browse files

Files changed (1) hide show

model.safetensors +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c12aeab8f6d8e8a5cbd8bd12a821acde7f37f64f99230adcb0b047ab0d7ef0
 size 2384234968

 version https://git-lfs.github.com/spec/v1
+oid sha256:e54d259f41701e99e426800728658954971e3999a08688f79f8bb3efbbcd8fb2
 size 2384234968