Instructions to use TheBloke/StableBeluga2-70B-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/StableBeluga2-70B-GGML with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/StableBeluga2-70B-GGML")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TheBloke/StableBeluga2-70B-GGML", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/StableBeluga2-70B-GGML with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/StableBeluga2-70B-GGML"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/StableBeluga2-70B-GGML",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/StableBeluga2-70B-GGML

SGLang

How to use TheBloke/StableBeluga2-70B-GGML 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 "TheBloke/StableBeluga2-70B-GGML" \
    --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": "TheBloke/StableBeluga2-70B-GGML",
		"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 "TheBloke/StableBeluga2-70B-GGML" \
        --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": "TheBloke/StableBeluga2-70B-GGML",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/StableBeluga2-70B-GGML with Docker Model Runner:
```
docker model run hf.co/TheBloke/StableBeluga2-70B-GGML
```

missing 70b in the name

by maddes8cht - opened Jul 28, 2023

Discussion

maddes8cht

Jul 28, 2023

•

edited Jul 28, 2023

This should have a 70b somewhere in the title, for else no one searching for 70b models will ever be able to find it.
I mean, it's almost 600 models in here now.
At the nous-hermes you named it
Nous-Hermes-Llama-2
At least the -2 got kind of convention for your llama-2 models.
Sticking to naming conventions gets increasingly important with that immense amount of models as thing cannot be found if a file is not named accordingly.
While, okay, 70b would be unique enough as there are no other 70b models around than Llama-2 .