{"id":16391610,"url":"https://github.com/philipmay/llm-data","last_synced_at":"2025-07-14T00:04:18.458Z","repository":{"id":231835606,"uuid":"782826294","full_name":"PhilipMay/llm-data","owner":"PhilipMay","description":"LLM Training Data","archived":false,"fork":false,"pushed_at":"2024-04-07T06:53:40.000Z","size":243,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-30T17:49:56.271Z","etag":null,"topics":["llm","sft"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/PhilipMay.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":"2024-04-06T06:24:26.000Z","updated_at":"2024-04-06T20:56:54.000Z","dependencies_parsed_at":"2024-04-06T07:26:02.327Z","dependency_job_id":"211f0725-543f-4187-964f-98a6fd2863c3","html_url":"https://github.com/PhilipMay/llm-data","commit_stats":null,"previous_names":["philipmay/llm-data"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/PhilipMay/llm-data","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhilipMay%2Fllm-data","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhilipMay%2Fllm-data/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhilipMay%2Fllm-data/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhilipMay%2Fllm-data/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PhilipMay","download_url":"https://codeload.github.com/PhilipMay/llm-data/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PhilipMay%2Fllm-data/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265224095,"owners_count":23730336,"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":["llm","sft"],"created_at":"2024-10-11T04:46:48.526Z","updated_at":"2025-07-14T00:04:18.433Z","avatar_url":"https://github.com/PhilipMay.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM Data\n\nThis repository is mainly about cleaning, converting and checking LLM training datasets.\n\n## Datasets\n\nNew datasets cleaned and created by this project:\n\n- [UltraChat-200k-ShareGPT-clean](https://huggingface.co/datasets/PhilipMay/UltraChat-200k-ShareGPT-clean)\n- [Nectar-ShareGPT-clean](https://huggingface.co/datasets/PhilipMay/Nectar-ShareGPT-clean)\n\n## Licensing\n\nCopyright (c) 2024 [Philip May](https://philipmay.org/)\n\nLicensed under the **MIT License** (the \"License\"); you may not use this file except in compliance with the License.\nYou may obtain a copy of the License by reviewing the file\n[LICENSE](https://github.com/PhilipMay/llm-data/blob/main/LICENSE) in the repository.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphilipmay%2Fllm-data","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fphilipmay%2Fllm-data","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphilipmay%2Fllm-data/lists"}