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
```

Is there integration with Langchain?

#24

by DesmondChoy - opened Aug 1, 2023

Discussion

DesmondChoy

Aug 1, 2023

I've checked https://python.langchain.com/docs/integrations/llms/ but I can't find options on integrating this with Langchain.
I've installed the 4-bit model and was hoping to use it for a Q&A use case.
Would appreciate any help, thank you!

GentlePickle

Aug 1, 2023

This isn't a question about or regarding the model. If you have the knowhow then you could integrate anything that generates text from input with langchain.

You can run any llama-architecture type model from a variety of frameworks, many of which have langchain integration. The simplest is probably transformers or CTransformers. Also pretty simple is running it with Oobabooga's textgen web UI, or any application like that that you can run and perform inference with. That tool comes with a variety of options for langchain integration, including blocking and streaming APIs, or just a local URL that you can plug right in to a langchain function. There's a whole massive section in the langchain documentation on which inference frameworks have supported packages.

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