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", 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
```

dmayhem93 commited on Jul 21, 2023

Commit

77ef3fd

1 Parent(s): b335bf4

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -6

README.md CHANGED Viewed

@@ -23,16 +23,16 @@ Start chatting with `FreeWilly2` using the following code snippet:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-tokenizer = AutoTokenizer.from_pretrained("stabilityai/FreeWilly2, use_fast=False)
-model = AutoModelForCausalLM.from_pretrained("stabilityai/FreeWilly2", torch_dtype=torch.float16, low_cpu_mem_usage=True, use_accelerate=True)
-generator = pipeline(model=model, tokenizer=tokenizer)
 system_prompt = "### System:\nYou are Free Willy, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
 message = "Write me a poem please"
 prompt = f"{system_prompt}### User: {message}\n\n### Assistant:\n"
-output = generator(prompt, num_return_sequences=1, do_sample=True, top_p=0.95, top_k=0)
-print(output)
 ```
 FreeWilly should be used with this prompt format:
@@ -102,4 +102,3 @@ Although the aforementioned dataset helps to steer the base language models into
       primaryClass={cs.CL}
 }
 ```

 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+tokenizer = AutoTokenizer.from_pretrained("stabilityai/FreeWilly2", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained("stabilityai/FreeWilly2", torch_dtype=torch.float16, low_cpu_mem_usage=True, device_map="auto")
 system_prompt = "### System:\nYou are Free Willy, an AI that follows instructions extremely well. Help as much as you can. Remember, be safe, and don't do anything illegal.\n\n"
 message = "Write me a poem please"
 prompt = f"{system_prompt}### User: {message}\n\n### Assistant:\n"
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+output = model.generate(**inputs, do_sample=True, top_p=0.95, top_k=0, max_new_tokens=256)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
 FreeWilly should be used with this prompt format:
       primaryClass={cs.CL}
 }
 ```