HuggingFaceTB
/

SmolLM-135M

Text Generation

text-generation-inference

Model card Files Files and versions

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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM-135M")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM-135M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM-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/SmolLM-135M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

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

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

Resources

View closed (6)

Listed on OpenModelMap

#24 opened 2 months ago by

Add EvalEval community eval results

#23 opened 5 months ago by

System prompt

#22 opened about 1 year ago by

Data Formatting

#21 opened over 1 year ago by

testing

#20 opened over 1 year ago by

Training details

#19 opened over 1 year ago by

EOS Token

#18 opened almost 2 years ago by

Benchmark results

#17 opened about 2 years ago by

Interview request: genAI evaluation & documentation

#16 opened about 2 years ago by

Are there two identical embedding tensors, even though embeddings are shared?

#15 opened about 2 years ago by

About MMLU evaluation

#12 opened about 2 years ago by

Intermediate checkpoints for research purposes

#11 opened about 2 years ago by

ONNX generation

#9 opened over 2 years ago by

Adding Evaluation Results

#8 opened over 2 years ago by

leaderboard-pr-bot

Google Colab for Guide to Use the Model

#7 opened over 2 years ago by

Model code for training from sractch

#6 opened over 2 years ago by

Multilingual Support

#5 opened over 2 years ago by

Trapezoidal scheduler with cooldown phase

#4 opened over 2 years ago by