{"id":18011195,"url":"https://github.com/marcelo-earth/light-tuning","last_synced_at":"2026-02-24T06:35:37.815Z","repository":{"id":190915418,"uuid":"683188284","full_name":"marcelo-earth/light-tuning","owner":"marcelo-earth","description":"🤖 CLI to fine-tune GPT-3.5 Turbo models rapidly. 💬","archived":false,"fork":false,"pushed_at":"2023-08-28T00:02:02.000Z","size":451,"stargazers_count":6,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-01-28T00:40:42.277Z","etag":null,"topics":["cli","fine-tuning","gpt-3","gpt-35-turbo","gpt-cli","openai"],"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/marcelo-earth.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":"2023-08-25T20:06:52.000Z","updated_at":"2024-06-27T21:34:11.000Z","dependencies_parsed_at":"2024-10-21T02:07:17.886Z","dependency_job_id":null,"html_url":"https://github.com/marcelo-earth/light-tuning","commit_stats":null,"previous_names":["360macky/light-tuning","marcelo-earth/light-tuning"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/marcelo-earth/light-tuning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcelo-earth%2Flight-tuning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcelo-earth%2Flight-tuning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcelo-earth%2Flight-tuning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcelo-earth%2Flight-tuning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/marcelo-earth","download_url":"https://codeload.github.com/marcelo-earth/light-tuning/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcelo-earth%2Flight-tuning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29774446,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-24T04:54:30.205Z","status":"ssl_error","status_checked_at":"2026-02-24T04:53:58.628Z","response_time":75,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["cli","fine-tuning","gpt-3","gpt-35-turbo","gpt-cli","openai"],"created_at":"2024-10-30T03:06:26.974Z","updated_at":"2026-02-24T06:35:37.785Z","avatar_url":"https://github.com/marcelo-earth.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg\n    src=\".github/logo.png\"\n    align=\"center\"\n    width=\"100\"\n    alt=\"LightTuning\"\n    title=\"LightTuning\"\n  /\u003e\n  \u003ch1 align=\"center\"\u003eLightTuning\u003c/h1\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  🤖 CLI to fine-tune GPT-3.5 Turbo models rapidly. 💬\n\u003c/p\u003e\n\n![Demo of Project](./.github/preview.jpg)\n\n## 🚀 Concept\n\n**LightTuning** is a quick way to fine-tune GPT-3.5 Turbo models. To scale and enhance a model from a small conversation to a light GPT-3.5 model that can overperform GPT-4. How cool is that?\n\n## 🧑‍💻 Usage\n\n### Installation\n\nInstall the required packages using pip.\n\n```bash\npip3 install -r requirements.txt\n```\n\nRun the `main.py` script to start the tool.\n\n```bash\npython3 main.py\n```\n\nYou will be greeted with a welcome message and a list of actions to choose from:\n\n- Generate dataset\n- Upload dataset\n- Fine-tune model\n- All\n\nSelect an action using the arrow keys and press Enter.\n\n### Generate Dataset\n\nIf you choose 'Generate dataset', you will be asked to provide the path to the seed conversation. If you don't provide a path, LightTuning will ask you to enter it.\n\nAdd a seed conversation to the file. The conversation should be in the following OpenAI conversation format:\n\n```json\n[\n  {\n    \"role\": \"system\",\n    \"content\": \"You are an assistant that can translate from English to Spanish.\"\n  },\n  {\n    \"role\": \"user\",\n    \"content\": \"Hello\"\n  },\n  {\n    \"role\": \"assistant\",\n    \"content\": \"Hola\"\n  },\n  {\n    \"role\": \"user\",\n    \"content\": \"Happy\"\n  },\n  {\n    \"role\": \"assistant\",\n    \"content\": \"Feliz\"\n  }\n]\n```\n\n### Upload Dataset\n\nIf you choose 'Upload dataset', you will be asked to enter the path to the dataset file. If you don't provide a path, the tool will ask you to enter it. You will then be asked to confirm the upload.\n\n### Fine-tune Model\n\nIf you choose 'Fine-tune model', you will be asked to provide the file ID for fine-tuning. If you don't provide a file ID, the tool will ask you to enter it.\n\n### All\n\nIf you choose 'All', the tool will execute all of the above actions in order.\n\n## 📃 License\n\nDistributed under the MIT License.\nSee [`LICENSE`](./LICENSE) for more information.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarcelo-earth%2Flight-tuning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmarcelo-earth%2Flight-tuning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarcelo-earth%2Flight-tuning/lists"}