SSM
Collection
Small Speculative Models • 2 items • Updated
How to use from
SGLangUse 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 "double7/vicuna-68m" \
--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": "double7/vicuna-68m",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Model description
This is a Vicuna-like model with only 68M parameters, which is fine-tuned from LLaMA-68m on ShareGPT data.
The training setup follows the Vicuna suite.
The model is mainly developed as a base Small Speculative Model in the MCSD paper. As a comparison, it can be better aligned to the Vicuna models than LLaMA-68m with little loss of alignment to the LLaMA models.
| Draft Model | Target Model | Alignment |
|---|---|---|
| LLaMA-68/160M | LLaMA-13/33B | 😃 |
| LLaMA-68/160M | Vicuna-13/33B | 😟 |
| Vicuna-68/160M | LLaMA-13/33B | 😃 |
| Vicuna-68/160M | Vicuna-13/33B | 😃 |
- Downloads last month
- 6,295
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "double7/vicuna-68m" \ --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": "double7/vicuna-68m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'