Instructions to use HuggingFaceTB/SmolLM2-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolLM2-1.7B with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM2-1.7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-1.7B")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-1.7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceTB/SmolLM2-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM2-1.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM2-1.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM2-1.7B

SGLang

How to use HuggingFaceTB/SmolLM2-1.7B 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 "HuggingFaceTB/SmolLM2-1.7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM2-1.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "HuggingFaceTB/SmolLM2-1.7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM2-1.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM2-1.7B with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM2-1.7B
```

Add link to Neuron-optimized version

by badaoui HF Staff - opened Aug 23, 2025

base: refs/heads/main

←

from: refs/pr/8

Discussion Files changed

+13

-1

Files changed (1) hide show

README.md +13 -1

README.md CHANGED Viewed

@@ -133,4 +133,16 @@ SmolLM2 models primarily understand and generate content in English. They can pr
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2502.02737},
 }
-```

       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2502.02737},
 }
+```
+---
+## 🚀 AWS Neuron Optimized Version Available
+A Neuron-optimized version of this model is available for improved performance on AWS Inferentia/Trainium instances:
+**[badaoui/HuggingFaceTB-SmolLM2-1.7B-neuron](https://huggingface.co/badaoui/HuggingFaceTB-SmolLM2-1.7B-neuron)**
+The Neuron-optimized version provides:
+- Pre-compiled artifacts for faster loading
+- Optimized performance on AWS Neuron devices
+- Same model capabilities with improved inference speed