{"id":18096651,"url":"https://github.com/andreaschandra/codet5-extended","last_synced_at":"2025-04-06T03:26:54.760Z","repository":{"id":182190638,"uuid":"668084099","full_name":"andreaschandra/CodeT5-extended","owner":"andreaschandra","description":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","archived":false,"fork":false,"pushed_at":"2023-07-28T08:02:56.000Z","size":11212,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-12T09:50:00.761Z","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":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/andreaschandra.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-07-19T01:57:04.000Z","updated_at":"2024-01-09T13:09:19.000Z","dependencies_parsed_at":"2025-02-12T09:50:06.090Z","dependency_job_id":null,"html_url":"https://github.com/andreaschandra/CodeT5-extended","commit_stats":null,"previous_names":["andreaschandra/codet5-extended"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreaschandra%2FCodeT5-extended","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreaschandra%2FCodeT5-extended/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreaschandra%2FCodeT5-extended/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreaschandra%2FCodeT5-extended/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/andreaschandra","download_url":"https://codeload.github.com/andreaschandra/CodeT5-extended/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247430098,"owners_count":20937812,"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":"2024-10-31T19:15:00.659Z","updated_at":"2025-04-06T03:26:54.729Z","avatar_url":"https://github.com/andreaschandra.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CodeT5 and CodeT5+\n\nOfficial research release for  **CodeT5** and **CodeT5+** models for **Code Understanding and Generation** from Salesforce Research, which are introduced by the following papers:\n\n*Title*: [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://arxiv.org/pdf/2305.07922.pdf)\n\n\u003e *Authors*: [Yue Wang](https://yuewang-cuhk.github.io/)\\*, [Hung Le](https://sites.google.com/view/henryle2018/home?pli=1)\\*, [Akhilesh Deepak Gotmare](https://akhileshgotmare.github.io/), [Nghi D.Q. Bui](https://bdqnghi.github.io/), [Junnan Li](https://sites.google.com/site/junnanlics), [Steven C.H. Hoi](https://sites.google.com/view/stevenhoi/home) (* indicates equal contribution)\n\n*Title*: [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://arxiv.org/pdf/2109.00859.pdf)\n\n\u003e *Authors*: [Yue Wang](https://yuewang-cuhk.github.io/), [Weishi Wang](https://www.linkedin.com/in/weishi-wang/)\n, [Shafiq Joty](https://raihanjoty.github.io/), [Steven C.H. Hoi](https://sites.google.com/view/stevenhoi/home)\n\n\nIn practice, CodeT5 and CodeT5+ models can be deployed as an AI-powered coding assistant to boost the productivity of software developers.\nAt Salesforce, we build an AI coding assistant demo using CodeT5 as a VS Code plugin to provide three capabilities:\n\n- **Text-to-code generation**: generate code based on the natural language description.\n- **Code autocompletion**: complete the whole function of code given the target function name.\n- **Code summarization**: generate the summary of a function in natural language description.\n\n![CodeT5 demo](./codet5.gif)\n\n## What's New: 🎉 \n\n**May 2023**\n\n**CodeT5+** paper and models are released！🔥 \u003cbr\u003e\n[paper](https://arxiv.org/pdf/2305.07922.pdf) | [code](https://github.com/salesforce/CodeT5/tree/main/CodeT5+) | [model](https://huggingface.co/models?sort=downloads\u0026search=codet5p) | [blog](https://blog.salesforceairesearch.com/codet5-open-code-large-language-models/)\n\n**Sep 2022**\n\nOur **CodeRL** paper has been accepted to NeurIPS 2022! \u003cbr\u003e\n[paper](https://arxiv.org/pdf/2207.01780.pdf) | [code](https://github.com/salesforce/CodeRL) | [blog](https://blog.salesforceairesearch.com/coderl) \n\n\n**July 2022**\n\nWe release two large-sized CodeT5 checkpoints at HuggingFace: [Salesforce/codet5-large](https://huggingface.co/Salesforce/codet5-large) and [Salesforce/codet5-large-ntp-py](https://huggingface.co/Salesforce/codet5-large-ntp-py), which are introduced by the [CodeRL paper](https://arxiv.org/pdf/2207.01780.pdf).\n\n**Oct 2021**\n\nWe release [fine-tuned checkpoints](https://console.cloud.google.com/storage/browser/sfr-codet5-data-research/finetuned_models)\nfor all the downstream tasks covered in the paper.\nBesides, we release a CodeT5-base fine-tuned\ncheckpoint ([Salesforce/codet5-base-multi-sum](https://huggingface.co/Salesforce/codet5-base-multi-sum)) for\nmultilingual code summarization. \n\n\n**Sep, 2021**\n\n**CodeT5** paper accepted to EMNLP 2021 and models are released! \u003cbr\u003e\n[paper](https://arxiv.org/pdf/2109.00859.pdf) | [code](https://github.com/salesforce/CodeT5/tree/main/CodeT5) | [model](https://huggingface.co/models?sort=downloads\u0026search=codet5) | [model card](https://github.com/salesforce/CodeT5/blob/main/CodeT5/CodeT5_model_card.pdf) | [blog](https://blog.salesforceairesearch.com/codet5/) \n\n\n\n\n\n## Citation\n\nIf you find this code to be useful for your research, please consider citing:\n\n```\n@inproceedings{\n    wang2021codet5,\n    title={CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation}, \n    author={Yue Wang, Weishi Wang, Shafiq Joty, Steven C.H. Hoi},\n    booktitle={EMNLP},\n    year={2021},\n}\n\n@inproceedings{\n    le2022coderl,\n    title={CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning},\n    author={Le, Hung and Wang, Yue and Gotmare, Akhilesh Deepak and Savarese, Silvio and Hoi, Steven C. H.},\n    booktitle={NeurIPS},\n    year={2022}\n}\n\n@article{\n    wang2023codet5plus,\n    title={CodeT5+: Open Code Large Language Models for Code Understanding and Generation},\n    author={Wang, Yue and Le, Hung and Gotmare, Akhilesh Deepak and Bui, Nghi D.Q. and Li, Junnan and Hoi, Steven C. H.},\n    journal={arXiv preprint},\n    year={2023}\n}\n```\n\n## License\n\nThe code is released under the BSD-3 License (see `LICENSE.txt` for details), but we also ask that users respect the\nfollowing:\n\nThis software should not be used to promote or profit from:\n\nviolence, hate, and division,\n\nenvironmental destruction,\n\nabuse of human rights, or\n\nthe destruction of people's physical and mental health.\n\nWe encourage users of this software to tell us about the applications in which they are putting it to use by emailing\ncodeT5@salesforce.com, and to\nuse [appropriate](https://arxiv.org/abs/1810.03993) [documentation](https://www.partnershiponai.org/about-ml/) when\ndeveloping high-stakes applications of this model.\n\n\n## Get Involved\n\nPlease create a GitHub issue if you have any questions, suggestions, requests or bug-reports. We welcome PRs!\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandreaschandra%2Fcodet5-extended","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fandreaschandra%2Fcodet5-extended","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandreaschandra%2Fcodet5-extended/lists"}