{"id":21749003,"url":"https://github.com/jcolechanged/sage-rl","last_synced_at":"2026-05-11T04:48:02.456Z","repository":{"id":240435390,"uuid":"799338957","full_name":"jColeChanged/sage-rl","owner":"jColeChanged","description":null,"archived":false,"fork":false,"pushed_at":"2024-05-18T20:21:44.000Z","size":99,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-25T23:03:31.096Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jColeChanged.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-11T20:45:40.000Z","updated_at":"2024-05-18T20:21:47.000Z","dependencies_parsed_at":"2024-05-18T21:28:02.536Z","dependency_job_id":"29334dad-e572-4050-bf4f-cf67e4a1212e","html_url":"https://github.com/jColeChanged/sage-rl","commit_stats":null,"previous_names":["jcolechanged/sage-rl"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jColeChanged%2Fsage-rl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jColeChanged%2Fsage-rl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jColeChanged%2Fsage-rl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jColeChanged%2Fsage-rl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jColeChanged","download_url":"https://codeload.github.com/jColeChanged/sage-rl/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244724611,"owners_count":20499459,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-26T08:16:02.649Z","updated_at":"2026-05-11T04:48:02.412Z","avatar_url":"https://github.com/jColeChanged.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Finetuning and RLHF scripts for the [Guild of the Rose](https://guildoftherose.org/)\nSage AI.  Based off the HuggingFace [TRL library](https://github.com/huggingface/trl).\n\n## Getting Started\n\nStep 1. Install [CUDA](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/)\nStep 2. Install [Python](https://www.python.org/)\nStep 3. Create a virtual environment and install dependencies into it.\n\n```python\npython3 -m venv env\nsource env/bin/activate\npip install -r requirements.txt\n```\n\nStep 4.  Before you can do training you'll need to configure your accelerate config.\n\n```bash\naccelerate config\n```\n\nOnce the accelerator is in place you can do supervised fine-tuning with:\n\n```bash\ntrl sft --model_name_or_path facebook/opt-125m --dataset_name imdb --output_dir opt-sft-imdb\n```\n\nDirect policy optimization with:\n\n```bash\ntrl dpo --model_name_or_path facebook/opt-125m --output_dir trl-hh-rlhf --dataset_name trl-internal-testing/hh-rlhf-trl-style\n````\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjcolechanged%2Fsage-rl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjcolechanged%2Fsage-rl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjcolechanged%2Fsage-rl/lists"}