Instructions to use stabilityai/StableBeluga2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stabilityai/StableBeluga2 with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/StableBeluga2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stabilityai/StableBeluga2")
model = AutoModelForCausalLM.from_pretrained("stabilityai/StableBeluga2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use stabilityai/StableBeluga2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stabilityai/StableBeluga2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/StableBeluga2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stabilityai/StableBeluga2

SGLang

How to use stabilityai/StableBeluga2 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 "stabilityai/StableBeluga2" \
    --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": "stabilityai/StableBeluga2",
		"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 "stabilityai/StableBeluga2" \
        --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": "stabilityai/StableBeluga2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stabilityai/StableBeluga2 with Docker Model Runner:
```
docker model run hf.co/stabilityai/StableBeluga2
```

License Change

#20

by bspence08 - opened Jul 27, 2023

Discussion

bspence08

Jul 27, 2023

Hi, congrats on the model! We noticed the Llama 2 Community License is not included in the Model Details section. Per the terms of the agreement, companies who build with Llama 2 need to present the 1) Community License 2) Acceptable Use Policy and 3) Responsible Use Guide when publishing. Please make the change to include these with respect to the base model (Llama 2).

bspence08 changed discussion status to closed Jul 27, 2023

bspence08 changed discussion title from License Change to Delete Jul 27, 2023

bspence08 changed discussion status to open Jul 27, 2023

bspence08 changed discussion title from Delete to License Change Jul 27, 2023

claforte

Jul 28, 2023

We added the files to the models and we're double-checking with our Legal if there's any extra steps that are still required. Thank you for your understanding!

claforte

Jul 28, 2023

See: https://huggingface.co/stabilityai/StableBeluga2/tree/main/LLAMA%202%20LICENSE
There are currently duplicates of some of these files - we'll likely delete them soon.

bspence08

Jul 28, 2023

Thank you! Really appreciate the quick resolution.

Andreas222

Aug 15, 2023

Doesn't the llama 2 license apply to all derivative work as well? As I read the license you can't have your own license on this model?

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