Instructions to use stabilityai/StableBeluga1-Delta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stabilityai/StableBeluga1-Delta with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/StableBeluga1-Delta")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("stabilityai/StableBeluga1-Delta")
model = AutoModelForMultimodalLM.from_pretrained("stabilityai/StableBeluga1-Delta")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stabilityai/StableBeluga1-Delta with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stabilityai/StableBeluga1-Delta"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/StableBeluga1-Delta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stabilityai/StableBeluga1-Delta

SGLang

How to use stabilityai/StableBeluga1-Delta 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/StableBeluga1-Delta" \
    --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/StableBeluga1-Delta",
		"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/StableBeluga1-Delta" \
        --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/StableBeluga1-Delta",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stabilityai/StableBeluga1-Delta with Docker Model Runner:
```
docker model run hf.co/stabilityai/StableBeluga1-Delta
```

dmayhem93 commited on Jul 27, 2023

Commit

76c8c4f

1 Parent(s): d1c7137

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ pipeline_tag: text-generation
 ### Apply Delta Weights
-Stable Beluga 1 cannot be used from the `stabilityai/StableBeluga1-Delta` weights alone. To obtain the correct model, one must add back the difference between LLaMA 65B and `stabilityai/FreeWilly1-Delta-SafeTensor` weights. We provide the [`apply_delta.py`](https://huggingface.co/stabilityai/FreeWilly1-Delta-SafeTensor/raw/main/apply_delta.py) script to automate the conversion, which you can run as:
 ```sh
@@ -74,7 +74,7 @@ The output of Stable Beluga 1
 ### Training Dataset
-`FreeWilly` is trained on our internal Orca-style dataset
 ### Training Procedure

 ### Apply Delta Weights
+Stable Beluga 1 cannot be used from the `stabilityai/StableBeluga1-Delta` weights alone. To obtain the correct model, one must add back the difference between LLaMA 65B and `stabilityai/StableBeluga1-Delta` weights. We provide the [`apply_delta.py`](https://huggingface.co/stabilityai/StabelBeluga1-Delta/raw/main/apply_delta.py) script to automate the conversion, which you can run as:
 ```sh
 ### Training Dataset
+`Stable Beluga 1` is trained on our internal Orca-style dataset
 ### Training Procedure