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")

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```

StableBeluga2

Commit History

Apr 11, 2024

13:42
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
4eb9f82

Sep 18, 2023

15:55
Update generation_config.json

dmayhem93

cb47d3d

Aug 29, 2023

20:20
add stable chat

dmayhem93

effbf4c

Jul 31, 2023

20:08
Update README.md

dmayhem93

c0e9122
20:08
Update README.md

dmayhem93

21d30d0

Jul 28, 2023

20:50
Delete USE_POLICY.md

dmayhem93

3e379cc
20:49
Delete Responsible-Use-Guide.pdf

dmayhem93

6b4cb4e
20:49
Delete Notice

dmayhem93

bddbe5a
20:49
Delete LLAMA 2 LICENSE.txt

dmayhem93

e8b32eb
20:49
Delete llama2

dmayhem93

1c238c8
14:08
Upload 3 files

dmayhem93

2e16a9f
13:36
Upload Responsible-Use-Guide.pdf

dmayhem93

ef17685

Jul 27, 2023

18:54
Update README.md

dmayhem93

46f3ebc
18:51
Update README.md

dmayhem93

3b77dcd
18:44
Update README.md

dmayhem93

863ba93
18:44
Update README.md

dmayhem93

5187e8d
18:39
Upload 4 files

dmayhem93

45efbd5
18:38
Update README.md

dmayhem93

c0be934

Jul 21, 2023

19:43
Update config.json

dmayhem93

aceb6bf
19:43
Update tokenizer_config.json

dmayhem93

d834a43
19:18
Update README.md

dmayhem93

77ef3fd
18:45
Create README.md (#1)⁠

ncoop57 +1: dmayhem93

b335bf4
18:19
add llama2 licenses, notice, readme, and use_policy

dmayhem93

ad7e151

Jul 20, 2023

15:59
Upload tokenizer

dmayhem93

e4944ca
15:58
Upload LlamaForCausalLM

dmayhem93

9e50dee
15:09
initial commit

dmayhem93

5d4ec28

Commit History

Apr 11, 2024

Adding `safetensors` variant of this model⁠

Sep 18, 2023

Update generation_config.json

Aug 29, 2023

add stable chat

Jul 31, 2023

Update README.md

Update README.md

Jul 28, 2023

Delete USE_POLICY.md

Delete Responsible-Use-Guide.pdf

Delete Notice

Delete LLAMA 2 LICENSE.txt

Delete llama2

Upload 3 files

Upload Responsible-Use-Guide.pdf

Jul 27, 2023

Update README.md

Update README.md

Update README.md

Update README.md

Upload 4 files

Update README.md

Jul 21, 2023

Update config.json

Update tokenizer_config.json

Update README.md

Create README.md (#1)⁠

add llama2 licenses, notice, readme, and use_policy

Jul 20, 2023

Upload tokenizer

Upload LlamaForCausalLM

initial commit