Text Generation
Transformers
Safetensors
rag
commit-message-generation
hyperbolic-geometry
software-maintenance
reproducible-research
Instructions to use Malolmalsky/rag-hyp-commit-message-generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Malolmalsky/rag-hyp-commit-message-generation with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Malolmalsky/rag-hyp-commit-message-generation")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Malolmalsky/rag-hyp-commit-message-generation", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Malolmalsky/rag-hyp-commit-message-generation with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Malolmalsky/rag-hyp-commit-message-generation" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Malolmalsky/rag-hyp-commit-message-generation", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Malolmalsky/rag-hyp-commit-message-generation
- SGLang
How to use Malolmalsky/rag-hyp-commit-message-generation 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 "Malolmalsky/rag-hyp-commit-message-generation" \ --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": "Malolmalsky/rag-hyp-commit-message-generation", "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 "Malolmalsky/rag-hyp-commit-message-generation" \ --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": "Malolmalsky/rag-hyp-commit-message-generation", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Malolmalsky/rag-hyp-commit-message-generation with Docker Model Runner:
docker model run hf.co/Malolmalsky/rag-hyp-commit-message-generation
| { | |
| "schema": "rag-hyp-hf-checkpoint/v1", | |
| "repo_id": "Malolmalsky/rag-hyp-commit-message-generation", | |
| "created_at": "2026-06-01T13:02:12.661366+00:00", | |
| "checkpoint_name": "checkpoint-170000", | |
| "base_model": "facebook/rag-sequence-base", | |
| "dataset": { | |
| "id": "Malolmalsky/new-commits", | |
| "url": "https://huggingface.co/datasets/Malolmalsky/new-commits" | |
| }, | |
| "files": [ | |
| { | |
| "repo_path": "checkpoint-170000/config.json", | |
| "local_name": "config.json", | |
| "bytes": 5959, | |
| "sha256": "d4d3f41b44c41c7795a2717e6f5c8d0bebf93f5cf0f3f0e6c0ebad720aaaf93b" | |
| }, | |
| { | |
| "repo_path": "checkpoint-170000/model.safetensors", | |
| "local_name": "model.safetensors", | |
| "bytes": 2061032996, | |
| "sha256": "4f1b9e1837998652bdbf6fdf1aa9fc3e006b99d72d312fcb11eab7048e73b1ef" | |
| } | |
| ] | |
| } | |