{"id":13754197,"url":"https://github.com/EleutherAI/math-lm","last_synced_at":"2025-05-09T22:31:28.916Z","repository":{"id":76772492,"uuid":"596330931","full_name":"EleutherAI/math-lm","owner":"EleutherAI","description":null,"archived":false,"fork":false,"pushed_at":"2024-03-12T05:10:40.000Z","size":19734,"stargazers_count":1077,"open_issues_count":15,"forks_count":88,"subscribers_count":18,"default_branch":"main","last_synced_at":"2025-04-09T11:08:15.459Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EleutherAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2023-02-02T00:16:35.000Z","updated_at":"2025-04-08T07:15:51.000Z","dependencies_parsed_at":"2023-07-20T09:45:13.832Z","dependency_job_id":"679156c3-4ea6-4dd6-b3ad-71ff29d06fb2","html_url":"https://github.com/EleutherAI/math-lm","commit_stats":null,"previous_names":["eleutherai/math-lm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fmath-lm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fmath-lm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fmath-lm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EleutherAI%2Fmath-lm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EleutherAI","download_url":"https://codeload.github.com/EleutherAI/math-lm/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253335675,"owners_count":21892713,"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":"2024-08-03T09:01:49.266Z","updated_at":"2025-05-09T22:31:28.488Z","avatar_url":"https://github.com/EleutherAI.png","language":"Python","funding_links":[],"categories":["A01_文本生成_文本对话","Python","🤖 Foundation Models for Science","EleutherAI"],"sub_categories":["大语言对话模型及数据","General Science Models"],"readme":"# `Llemma`: an open language model for mathematics\n\n\u003cimg src=\"./llemma.jpg\" width=\"50%\"/\u003e\n  \n[ArXiv](http://arxiv.org/abs/2310.10631) | [Models](https://huggingface.co/EleutherAI/llemma_34b) | [Data](https://huggingface.co/datasets/EleutherAI/proof-pile-2) | [Code](https://github.com/EleutherAI/math-lm) | [Blog](https://blog.eleuther.ai/llemma/) | [Sample Explorer](https://llemma-demo.github.io/)\n\nRepository for [Llemma: an open language model for mathematics [Azerbayev et al 2023]](https://arxiv.org/abs/2310.10631).\n\nThis repository hosts data and training code related to the following artifacts:\n\n| Name | HF Hub Link |\n| ---------- | ------------------ | \n| **Llemma 7b** |[`EleutherAI/llemma_7b`](https://huggingface.co/EleutherAI/llemma_7b)  | \n| **Llemma 34b** |[`EleutherAI/llemma_34b`](https://huggingface.co/EleutherAI/llemma_34b)  | \n| **Proof-Pile-2** |[`EleutherAI/ProofPile2`](https://huggingface.co/datasets/EleutherAI/proof-pile-2)  | \n| **AlgebraicStack** |[`EleutherAI/AlgebraicStack`](https://huggingface.co/datasets/EleutherAI/proof-pile-2/tree/main/algebraic-stack)  | \n\nThis repository also contains submodules related to the overlap, fine-tuning, and theorem proving experiments described in the paper.\nAdditional evaluation code is in a [fork of the Eleuther LM Evaluation Harness](https://github.com/wellecks/lm-evaluation-harness).\n\n## Directories \nThis repository contains the following directories\n- `proof_pile_2`: scripts for downloading and preprocessing data.\n- `gpt-neox`: git submodule containing a modified branch of `EleutherAI/gpt-neox`\n- `lm-evaluation-harness`: code for all evaluations, except formal2formal theorem proving.\n- `llemma_formal2formal`: git submodule containing scripts for the formal2formal experiments\n- `overlap`: git submodule containing the overlap and memorization analysis \n- `finetunes`: git submodule containing scripts for the fine-tuning experiments\n\nBecause this project contains submodules, you should clone this project with the `--recurse-submodules` flag or, alternatively, run `git submodule update --init --recursive` from within the project directory after cloning the project. After running `git pull`, you should also run `git submodule update`.\n\n## Citation\nPlease cite the following:\n```\n@article{azerbayev2023llemma,\n  title={Llemma: An Open Language Model For Mathematics}, \n  author={Azerbayev, Zhangir and Schoelkopf, Hailey and Paster, Keiran and Dos Santos, Marco and McAleer, Stephen and Jiang, Albert Q. and Deng, Jia and Biderman, Stella and Welleck, Sean},\n  journal={arXiv preprint arXiv:2310.06786},\n  year={2023}\n}\n```\n\nYou may also be interested in citing our training data, which is a mix of novel data and data from the following sources:\n```\n@article{paster2023openwebmath,\n  title={OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text},\n  author={Paster, Keiran and Santos, Marco Dos and Azerbayev, Zhangir and Ba, Jimmy},\n  journal={arXiv preprint arXiv:2310.06786},\n  year={2023}\n}\n\n@software{together2023redpajama,\n  author = {Together Computer},\n  title = {RedPajama: An Open Source Recipe to Reproduce LLaMA training dataset},\n  month = April,\n  year = 2023,\n  url = {https://github.com/togethercomputer/RedPajama-Data}\n}\n\n@article{kocetkov2022stack,\n  title={The stack: 3 tb of permissively licensed source code},\n  author={Kocetkov, Denis and Li, Raymond and Allal, Loubna Ben and Li, Jia and Mou, Chenghao and Ferrandis, Carlos Mu{\\~n}oz and Jernite, Yacine and Mitchell, Margaret and Hughes, Sean and Wolf, Thomas and Bahdanau, Dzmitry and von Werra, Leandro and de Vries, Harm},\n  journal={arXiv preprint arXiv:2211.15533},\n  year={2022}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEleutherAI%2Fmath-lm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FEleutherAI%2Fmath-lm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEleutherAI%2Fmath-lm/lists"}