Instructions to use TheBloke/orca_mini_v2_7B-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/orca_mini_v2_7B-GGML with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TheBloke/orca_mini_v2_7B-GGML")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TheBloke/orca_mini_v2_7B-GGML", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TheBloke/orca_mini_v2_7B-GGML with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheBloke/orca_mini_v2_7B-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/orca_mini_v2_7B-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TheBloke/orca_mini_v2_7B-GGML
- SGLang
How to use TheBloke/orca_mini_v2_7B-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/orca_mini_v2_7B-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/orca_mini_v2_7B-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/orca_mini_v2_7B-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/orca_mini_v2_7B-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TheBloke/orca_mini_v2_7B-GGML with Docker Model Runner:
docker model run hf.co/TheBloke/orca_mini_v2_7B-GGML
Config file missing for ctransformers
Hi mate, I am trying to run this model using just the HuggingFace model id and I am getting this error:
OSError: TheBloke/orca_mini_v2_7B-GGML does not appear to have a file named config.json. Checkout 'https://huggingface.co/TheBloke/orca_mini_v2_7B-GGML/main' for available files.
Are you planning to add a config.json file?
Love your work BTW :)
Yeah I do plan to at some point. It's added to new GGML repos, and I always added it for non-llama models, but it's not in most of the llama GGML repos
In the meantime just add model_type="llama" to your ctransformers call and it won't need to read config.json
Thank you, will do :)