{"id":20333399,"url":"https://github.com/ryhkml/fine-tune-forge","last_synced_at":"2025-04-11T21:41:07.229Z","repository":{"id":217988700,"uuid":"745296050","full_name":"ryhkml/fine-tune-forge","owner":"ryhkml","description":"JSONL generator designed for models like Google PaLM 2 and OpenAI GPT-3.5","archived":false,"fork":false,"pushed_at":"2024-12-11T03:26:35.000Z","size":1794,"stargazers_count":7,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-25T17:47:45.050Z","etag":null,"topics":["ai","fine-tuning","gpt-3","image-ocr","jsonl","openai","tool"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","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/ryhkml.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":"2024-01-19T02:56:50.000Z","updated_at":"2025-01-28T19:28:28.000Z","dependencies_parsed_at":"2024-03-05T05:27:11.381Z","dependency_job_id":"11d106d4-5655-4f74-9f6a-872695564ca8","html_url":"https://github.com/ryhkml/fine-tune-forge","commit_stats":null,"previous_names":["ryhkml/fine-tune-forge"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryhkml%2Ffine-tune-forge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryhkml%2Ffine-tune-forge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryhkml%2Ffine-tune-forge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ryhkml%2Ffine-tune-forge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ryhkml","download_url":"https://codeload.github.com/ryhkml/fine-tune-forge/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248486394,"owners_count":21112089,"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":["ai","fine-tuning","gpt-3","image-ocr","jsonl","openai","tool"],"created_at":"2024-11-14T20:31:16.673Z","updated_at":"2025-04-11T21:41:07.215Z","avatar_url":"https://github.com/ryhkml.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n    \u003ch1\u003e\n        \u003cb\u003eFineTuneForge\u003c/b\u003e\n    \u003c/h1\u003e\n\u003c/div\u003e\n\nFineTuneForge is a tool designed specifically for generating JSON Lines (JSONL) to facilitate the fine-tuning of AI language models like Google's PaLM 2 and OpenAI's GPT-3.5. It enables developers to easily transform text data into a JSONL format that machines can read.\n\n![Screenshot FineTuneForge Webapp](./Screenshot%20FineTuneForge%20Webapp.png)\n\n## Getting Started\n\n\u003e [!WARNING]\n\u003e\n\u003e DO NOT USE IN PRODUCTION\n\u003e\n\u003e This project has no CSRF protection. I'm unsure if i will implement it. For example, i created a new CSRF protection in Angular SSR 18. See it [here](https://github.com/ryhkml/angular-double-csrf-protection)\n\nTo get started with FineTuneForge, follow these steps:\n\n### Installation\n\n```sh\ngit clone https://github.com/ryhkml/fine-tune-forge.git\ncd fine-tune-forge\nsh install.sh\n```\n\n### Usage\n\nRun the JSONL generator with the following command:\n\n```sh\nnpm run build\n```\n\nServe server\n\n```sh\nnpm run serve\n```\n\n## Directory Structure\n\nFineTuneForge is organized into several directories, each serving a specific purpose in the workflow of the JSONL generator. Below is an overview of these directories and their intended use:\n\n-   `DATADOC_OCR`: This directory acts as a temporary storage for OCR (Optical Character Recognition) images\n-   `DATASET`: The `DATASET` directory is the designated location for storing the completed dataset files. Once the JSONL files have been generated and are ready for use in fine-tuning the language models, they are placed in this directory\n-   `DATATMP`: This directory for temporary storage of instruction content\n-   `tls`: This directory is reserved for storing SSL/TLS certificates\n\n## Configuring SSL/TLS for HTTPS\n\nTo enable HTTPS in the application, you need to configure SSL/TLS certificates correctly.\n\n### Required Files\n\nBefore you start, ensure you have the following files placed in the `tls` directory:\n\n-   `fullchain.pem`: This is your certificate file that contains the full chain of trust, including any intermediate certificates along with your own\n-   `cert-key.pem`: This file contains your private key and must be kept secure. It is used to establish the encrypted connection\n-   `ca.crt` (optional): This Certificate Authority (CA) file is used if you need to specify an external CA\n\nIf you use docker, uncomment the environment variable `PROTOCOL_SERVER` in `docker-compose.yaml`\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](./LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryhkml%2Ffine-tune-forge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fryhkml%2Ffine-tune-forge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryhkml%2Ffine-tune-forge/lists"}