Instructions to use HuggingFaceTB/SmolLM2-135M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolLM2-135M with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM2-135M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM2-135M")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM2-135M")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceTB/SmolLM2-135M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM2-135M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM2-135M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM2-135M

SGLang

How to use HuggingFaceTB/SmolLM2-135M 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/SmolLM2-135M" \
    --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/SmolLM2-135M",
		"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/SmolLM2-135M" \
        --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/SmolLM2-135M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM2-135M with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM2-135M
```

Is there no BOS token?

by viktor-shcherb - opened Feb 28, 2025

Discussion

viktor-shcherb

Feb 28, 2025

There have been a number of studies suggesting that a BOS token is very important for Llama models. SmolLM models are architecturally based on Llama, but do they borrow the addition of BOS token from Llama as well?

It seems like by default, the token is not added by the model tokenizer. Is it a bug? Should we add it manually when using SmolLM models?

model_name = 'HuggingFaceTB/SmolLM2-135M'
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.encode('test', add_special_tokens=True)

Outputs [2129]. On the contrary, when Llama tokenizer is used,

model_name = 'meta-llama/Meta-Llama-3-8B'
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.encode('test', add_special_tokens=True)

The output is [128000, 1985], it adds the BOS token (128000)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment