Instructions to use TheBloke/StableBeluga-13B-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/StableBeluga-13B-GGML with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TheBloke/StableBeluga-13B-GGML")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TheBloke/StableBeluga-13B-GGML", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TheBloke/StableBeluga-13B-GGML with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheBloke/StableBeluga-13B-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/StableBeluga-13B-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TheBloke/StableBeluga-13B-GGML
- SGLang
How to use TheBloke/StableBeluga-13B-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/StableBeluga-13B-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/StableBeluga-13B-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/StableBeluga-13B-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/StableBeluga-13B-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TheBloke/StableBeluga-13B-GGML with Docker Model Runner:
docker model run hf.co/TheBloke/StableBeluga-13B-GGML
Download stablebeluga-13b.ggmlv3.q2_K.bin from TheBloke/StableBeluga-13B-GGML: direct link, hf CLI and curl.
- Browser
- Download file 5.51 GB
-
https://huggingface.co/TheBloke/StableBeluga-13B-GGML/resolve/main/stablebeluga-13b.ggmlv3.q2_K.bin
- Command line
-
hf download hf://TheBloke/StableBeluga-13B-GGML/stablebeluga-13b.ggmlv3.q2_K.bin
-
curl -L -o stablebeluga-13b.ggmlv3.q2_K.bin https://huggingface.co/TheBloke/StableBeluga-13B-GGML/resolve/main/stablebeluga-13b.ggmlv3.q2_K.bin
5.51 GB
- Xet hash:
- 0d89553483b9ca3b2d250f1392a5d348747d1d1f2c1e554e7f30cfaabfbdab28
- Size of remote file:
- 5.51 GB
- SHA256:
- 2b41d80055c4db2fd09a583391b7cb53e0eb7394f64fb52e2914f2ed1d6379da
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.