{"id":14902061,"url":"https://github.com/facebookresearch/RAM","last_synced_at":"2025-09-22T14:30:40.114Z","repository":{"id":245966948,"uuid":"729373183","full_name":"facebookresearch/RAM","owner":"facebookresearch","description":"A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).","archived":false,"fork":false,"pushed_at":"2025-01-09T16:45:00.000Z","size":4245,"stargazers_count":156,"open_issues_count":2,"forks_count":9,"subscribers_count":10,"default_branch":"main","last_synced_at":"2025-01-12T09:05:20.344Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/facebookresearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":"2023-12-09T03:12:21.000Z","updated_at":"2025-01-09T18:49:45.000Z","dependencies_parsed_at":"2024-06-25T04:28:26.674Z","dependency_job_id":"59a7f6d0-3814-4003-b96b-4c1c610f5d30","html_url":"https://github.com/facebookresearch/RAM","commit_stats":null,"previous_names":["facebookresearch/ram"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FRAM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FRAM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FRAM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2FRAM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/facebookresearch","download_url":"https://codeload.github.com/facebookresearch/RAM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233853927,"owners_count":18740559,"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":"2024-09-22T11:00:32.931Z","updated_at":"2025-09-22T14:30:39.605Z","avatar_url":"https://github.com/facebookresearch.png","language":"Python","funding_links":[],"categories":["Python","A01_文本生成_文本对话","Other Useful Resources"],"sub_categories":["大语言对话模型及数据","2022"],"readme":"# RAM\n## Introduction\nThis repository focuses on developing advanced algorithms and methods for RAM (Reasoning, Alignment, Memory).\n\n\u003c!---\n- [System 2 Attention (is something you might need too)](https://arxiv.org/pdf/2311.11829.pdf)\n- [Some things are more CRINGE than others: Preference Optimization with the Pairwise Cringe Loss](https://arxiv.org/pdf/2312.16682.pdf)\n\n## Installation\nTo install the project, clone the repository and install the required dependencies:\n```bash\ngit clone https://github.com/facebookresearch/RAM.git\ncd RAM\npip install -r requirements.txt\n```\n--\u003e\n\n## Projects\nPlease go to [Projects](projects/README.md) for a up-to-date list of projects released by RAM.\n\n\n\u003c!---\n## Data\nThe data needed to run our code is hosted on HuggingFace:\n- https://huggingface.co/OpenAssistant\n- https://huggingface.co/datasets/tatsu-lab/alpaca_eval\n\n## Model\nThe library needed to run our code is\n- [Llama from HuggignFace] (https://huggingface.co/docs/transformers/main/model_doc/llama?fbclid=IwAR2ZRhVnuKqngWTBjhOhuDgQLQ5yzTh573uAA_16bEMX3lerKSHCtdla31w).To run huggingface Llama models, make sure to convert your LLaMA checkpoint and tokenizer into HuggingFace format and store it at \u003cyour_path_to_hf_converted_llama_ckpt_and_tokenizer\u003e.\n- [Alpaca Eval](https://github.com/tatsu-lab/alpaca_eval) for any inference only Llama experiments.\n--\u003e\n\n## Contributing\nPlease read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests.\n\n## License\nThis project is licensed under the MIT License - see the `LICENSE` file for details. The license applies to the released data as well.\n\n## Contact\nRAM is currently maintained by Olga Golovneva, Ilia Kulikov, Janice Lan, Xian Li, Richard Pang, Sainbayar Sukhbaatar, Tianlu Wang, Jason Weston, Jing Xu, Jane Dwivedi-Yu, Ping Yu, Weizhe Yuan.\nFor any queries, please reach out to [Jing Xu](https://github.com/jxmsML).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2FRAM","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffacebookresearch%2FRAM","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2FRAM/lists"}