Instructions to use lewtun/SmolLM2-360M-OpenMathReasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lewtun/SmolLM2-360M-OpenMathReasoning with Transformers:

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

pipe = pipeline("text-generation", model="lewtun/SmolLM2-360M-OpenMathReasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lewtun/SmolLM2-360M-OpenMathReasoning")
model = AutoModelForCausalLM.from_pretrained("lewtun/SmolLM2-360M-OpenMathReasoning")
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 Settings

vLLM

How to use lewtun/SmolLM2-360M-OpenMathReasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lewtun/SmolLM2-360M-OpenMathReasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lewtun/SmolLM2-360M-OpenMathReasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lewtun/SmolLM2-360M-OpenMathReasoning

SGLang

How to use lewtun/SmolLM2-360M-OpenMathReasoning 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 "lewtun/SmolLM2-360M-OpenMathReasoning" \
    --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": "lewtun/SmolLM2-360M-OpenMathReasoning",
		"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 "lewtun/SmolLM2-360M-OpenMathReasoning" \
        --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": "lewtun/SmolLM2-360M-OpenMathReasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lewtun/SmolLM2-360M-OpenMathReasoning with Docker Model Runner:
```
docker model run hf.co/lewtun/SmolLM2-360M-OpenMathReasoning
```

lewtun HF Staff commited on 24 days ago

Commit

eab4232

verified ·

1 Parent(s): dbe37dc

Training in progress, step 3048

Browse files

Files changed (2) hide show

README.md +1 -22
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -8,7 +8,6 @@ tags:
 - hf_jobs
 - trackio:https://lewtun-mlintern-omr360m1.hf.space?project=huggingface&runs=smollm2-360m-openmath-cot-lr2e5-bs16&sidebar=collapsed
 - trl
-- ml-intern
 licence: license
 ---
@@ -58,24 +57,4 @@ Cite TRL as:
   url     = {https://github.com/huggingface/trl},
   year    = {2020}
 }
-```
-<!-- ml-intern-provenance -->
-## Generated by ML Intern
-This model repository was generated by [ML Intern](https://github.com/huggingface/ml-intern), an agent for machine learning research and development on the Hugging Face Hub.
-- Try ML Intern: https://smolagents-ml-intern.hf.space
-- Source code: https://github.com/huggingface/ml-intern
-## Usage
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-model_id = 'lewtun/SmolLM2-360M-OpenMathReasoning'
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
-```
-For non-causal architectures, replace `AutoModelForCausalLM` with the appropriate `AutoModel` class.

 - hf_jobs
 - trackio:https://lewtun-mlintern-omr360m1.hf.space?project=huggingface&runs=smollm2-360m-openmath-cot-lr2e5-bs16&sidebar=collapsed
 - trl
 licence: license
 ---
   url     = {https://github.com/huggingface/trl},
   year    = {2020}
 }
+```

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9279c3366a64168b737d97f0232c495f43321f48bbac95b51cd7d6cc554a9c5
 size 723674912

 version https://git-lfs.github.com/spec/v1
+oid sha256:607dde6eac3b92f8eaa62038f61073ec7b55eea5c06d9b029b61f9006f42ac05
 size 723674912