{"data":{"slug":"zyq-scut-rltf","name":"RLTF","tagline":"Accepted by Transactions on Machine Learning Research (TMLR)","github_url":"https://github.com/Zyq-scut/RLTF","owner":"Zyq-scut","repo":"RLTF","owner_avatar_url":"https://avatars.githubusercontent.com/u/66082575?v=4","primary_language":"Python","stars":134,"forks":7,"topics":[],"archived":false,"github_pushed_at":"2024-10-05T09:52:35+00:00","maintenance_label":"Dormant","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/zyq-scut-rltf","markdown_url":"https://www.graphcanon.com/tools/zyq-scut-rltf.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zyq-scut-rltf","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zyq-scut-rltf","description":"Accepted by Transactions on Machine Learning Research (TMLR)","homepage_url":null,"license":"BSD-3-Clause","open_issues":0,"watchers":2,"ai_summary":"A repository implementing reinforcement learning techniques for text generation, incorporating elements from CodeRL, APPS, and transformers.","readme_excerpt":"## Installation  \n\nThe code requires some dependencies as specified in `requirements.txt`. Please follow the relevant libraries to install or run: \n\n`pip install -r requirements.txt`\n\n---\n\n## License \n\nThe code is released under BSD 3-Clause - see `LICENSE.txt` for details.\n\nThis code is developed from other open source projects: including [CodeRL](https://github.com/salesforce/CodeRL), [APPS](https://github.com/hendrycks/apps/), and [transformers](https://github.com/huggingface/transformers). We thank the original contributors of these works for open-sourcing their valuable source codes.","github_created_at":"2023-06-30T03:24:16+00:00","created_at":"2026-07-11T23:44:30.775542+00:00","updated_at":"2026-10-07T06:00:30.792286+00:00","categories":[{"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":"apps","name":"apps"},{"slug":"bsd-license","name":"bsd-license"},{"slug":"code-rl","name":"code-rl"},{"slug":"open-source-contributions","name":"open-source-contributions"},{"slug":"python-dependencies","name":"python-dependencies"},{"slug":"reinforcement-learning","name":"reinforcement learning"},{"slug":"text-generation","name":"text-generation"},{"slug":"transformers","name":"transformers"}],"trust":{"provenance":{"is_fork":false,"github_id":660450114,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-10-07T06:00:30.014Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":731,"last_release_at":null,"stars_delta_30d":1,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":75,"high_count":0,"last_scan_at":"2026-07-11T23:44:37.403Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-10-07T06:00:30.486Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-10-07T06:00:30.486Z"},"license_spdx":{"value":"BSD-3-Clause","source":"github.license","observed_at":"2026-10-07T06:00:30.486Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use RLTF when you need advanced Reinforcement Learning models specifically tuned for text generation tasks.","If your project builds upon the work of CodeRL or APPS and requires seamless integration with transformer-based architectures."],"when_not_to_use":["Avoid RLTF if your project does not require reinforcement learning techniques, especially focused on text generation.","Do not use this tool if your work is incompatible with components from CodeRL, APPS, or transformers."],"source":"enrich:decision_facts","observed_at":"2026-07-17T03:02:47.519Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"RLTF implements reinforcement learning for text generation using elements from CodeRL, APPS, and transformers."}]}}