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

Libraries

How to use HuggingFaceTB/SmolLM-360M with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM-360M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM-360M")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM-360M")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceTB/SmolLM-360M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM-360M"
# 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-360M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM-360M

SGLang

How to use HuggingFaceTB/SmolLM-360M 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-360M" \
    --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-360M",
		"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-360M" \
        --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-360M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM-360M with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM-360M
```

Xenova HF Staff commited on Jul 15, 2024

Commit

714709f

verified ·

1 Parent(s): bd6885d

Upload ONNX weights

Browse files

Files changed (7) hide show

onnx/model.onnx +3 -0
onnx/model_bnb4.onnx +3 -0
onnx/model_fp16.onnx +3 -0
onnx/model_int8.onnx +3 -0
onnx/model_q4.onnx +3 -0
onnx/model_quantized.onnx +3 -0
onnx/model_uint8.onnx +3 -0

onnx/model.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f1f35ffad3f46f1bc643f428d9406c940b6f0228e5161b096eabd486ebd6f1
+size 1448301209

onnx/model_bnb4.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fe6f80fdd69e731caff803c9b5e5b7481b87002d52ce0fe72ba8c7d1196389
+size 366992362

onnx/model_fp16.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed8065d648e798752e6a3fb4fb3cea97b3bddee17462e1c8c2456c74d678cb6
+size 724701643

onnx/model_int8.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0441b9ae5482fdd0f1998763a28fa24f3946dfca37ef5db2e47a7a16955e508c
+size 363270670

onnx/model_q4.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5a01e9e92df5c2d1e8ae297bdbcc0a648ca69774b8fa2f5ec8d7cb8c805a08ba
+size 386651434

onnx/model_quantized.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:0441b9ae5482fdd0f1998763a28fa24f3946dfca37ef5db2e47a7a16955e508c
+size 363270670

onnx/model_uint8.onnx ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1093c22f701af8728c46bc83a660cd234edcc23c28edd329a00b63efffde12a4
+size 363270784