{"data":{"slug":"tloen-alpaca-lora","name":"alpaca-lora","tagline":"Instruct-tune LLaMA on consumer hardware","github_url":"https://github.com/tloen/alpaca-lora","owner":"tloen","repo":"alpaca-lora","owner_avatar_url":"https://avatars.githubusercontent.com/u/4811103?v=4","primary_language":"Jupyter Notebook","stars":18912,"forks":2180,"topics":[],"archived":false,"github_pushed_at":"2024-07-29T13:37:49+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/tloen-alpaca-lora","markdown_url":"https://www.graphcanon.com/tools/tloen-alpaca-lora.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tloen-alpaca-lora","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tloen-alpaca-lora","description":"Instruct-tune LLaMA on consumer hardware","homepage_url":null,"license":"Apache-2.0","open_issues":365,"watchers":150,"ai_summary":"Repository for instruct tuning LLaMA model using consumer-grade hardware with options to build and run via Docker.","readme_excerpt":"### Docker Setup & Inference\n\n1. Build the container image:\n\n```bash\ndocker build -t alpaca-lora .\n```\n\n2. Run the container (you can also use `finetune.py` and all of its parameters as shown above for training):\n\n```bash\ndocker run --gpus=all --shm-size 64g -p 7860:7860 -v ${HOME}/.cache:/root/.cache --rm alpaca-lora generate.py \\\n    --load_8bit \\\n    --base_model 'decapoda-research/llama-7b-hf' \\\n    --lora_weights 'tloen/alpaca-lora-7b'\n```\n\n3. Open `https://localhost:7860` in the browser\n\n---\n\n### Docker Compose Setup & Inference\n\n1. (optional) Change desired model and weights under `environment` in the `docker-compose.yml`\n\n2. Build and run the container\n\n```bash\ndocker-compose up -d --build\n```\n\n3. Open `https://localhost:7860` in the browser\n\n4. See logs:\n\n```bash\ndocker-compose logs -f\n```\n\n5. Clean everything up:\n\n```bash\ndocker-compose down --volumes --rmi all\n```","github_created_at":"2023-03-13T21:52:36+00:00","created_at":"2026-07-11T23:21:46.150976+00:00","updated_at":"2026-08-03T00:01:42.162393+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"consumer-hardware","name":"consumer hardware"},{"slug":"docker","name":"docker"},{"slug":"instruct-tune","name":"instruct-tune"},{"slug":"llama","name":"llama"},{"slug":"lora","name":"lora"}],"trust":{"provenance":{"is_fork":false,"github_id":613591358,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-03T00:01:41.157Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":734,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":28,"high_count":5,"last_scan_at":"2026-07-11T23:21:56.017Z","medium_count":12,"scan_profile":"deps","critical_count":1}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-03T00:01:41.589Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-03T00:01:41.589Z","managed_saas":false},"languages":{"value":["jupyter notebook","python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-03T00:01:41.589Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-03T00:01:41.589Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-03T00:01:41.589Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The source code is freely available under the Apache-2.0 license, but costs associated with hardware and cloud services for running Docker may apply."},"requirements":null,"constraints":{"persona":"developer_harness","pricing_model":"freemium"},"when_to_use":["When you have limited GPU resources but want to perform instruction-fine-tuning on the LLaMA model, and your setup supports basic Docker.","If you prefer working within a Jupyter Notebook environment to experiment and fine-tune language models using consumer-grade hardware."],"when_not_to_use":["When you require more advanced customization beyond what is offered through the `finetune.py` script parameters or Jupyter Notebook interface.","For teams with high-performance computing resources aiming for optimal performance, as alpaca-lora is optimized for use on consumer-grade hardware."],"source":"enrich:decision_facts","observed_at":"2026-07-16T22:11:39.299Z"},"constraint_facets":{"persona":"developer_harness","pricing_model":"freemium"},"decision_summary":[{"label":"Pricing","value":"freemium - The source code is freely available under the Apache-2.0 license, but costs associated with hardware and cloud services for running Docker may apply."},{"label":"Adopt for","value":"alpaca-lora is an instruct tuning repository for the LLaMA model designed to work with consumer-grade hardware through Docker integration."},{"label":"License detail","value":"The Apache-2.0 license applies, allowing wide-ranging reuse and distribution of the software, provided that copyright notices are included and applicable files accompany distributed executables."},{"label":"Persona","value":"developer harness"}]}}