{"id":23173394,"url":"https://github.com/ziweek/award-factory","last_synced_at":"2026-04-09T12:55:44.571Z","repository":{"id":257633447,"uuid":"799450840","full_name":"ziweek/award-factory","owner":"ziweek","description":"🎓 Showcasing Project, in 2024 Google Machine Learning Bootcamp - 🏆🤖 Award-Factory: Awards lovingly crafted for you by a hilariously talented generative AI! #Google #Gemma:2b #fine-tuning #quantization","archived":false,"fork":false,"pushed_at":"2025-02-05T16:45:26.000Z","size":16006,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-10T08:48:45.814Z","etag":null,"topics":["docker","docker-compose","fastapi","fine-tuning","gemma-2b","google","large-language-model","llama-cpp","nextjs","quantization"],"latest_commit_sha":null,"homepage":"https://award-factory.vercel.app","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/ziweek.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":"2024-05-12T07:18:56.000Z","updated_at":"2025-02-01T16:21:42.000Z","dependencies_parsed_at":null,"dependency_job_id":"acc72e2d-8d92-4eb8-a9ff-ad8c6df4f82d","html_url":"https://github.com/ziweek/award-factory","commit_stats":null,"previous_names":["ziweek/award-factory"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziweek%2Faward-factory","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziweek%2Faward-factory/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziweek%2Faward-factory/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ziweek%2Faward-factory/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ziweek","download_url":"https://codeload.github.com/ziweek/award-factory/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247268064,"owners_count":20911069,"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":["docker","docker-compose","fastapi","fine-tuning","gemma-2b","google","large-language-model","llama-cpp","nextjs","quantization"],"created_at":"2024-12-18T05:15:28.536Z","updated_at":"2025-12-30T23:07:56.029Z","avatar_url":"https://github.com/ziweek.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# award-factory\n\n\u003cimg src=\"./src/banner_notion.png\"/\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cbr/\u003e\n  \u003cstrong\u003e🎓 Showcasing Project, in 2024 Google Machine Learning Bootcamp 🎓\u003c/strong\u003e\n  \u003cbr/\u003e\n  \u003cbr/\u003e\n  \u003ca href='https://github.com/ziweek/award-factory/blob/main/README_KO.md'\u003e\n    KOREAN\n  \u003c/a\u003e\n  \u0026nbsp;|\u0026nbsp;\n  \u003ca href='https://github.com/ziweek/award-factory/blob/main/README.md'\u003e\n    ENGLISH\n  \u003c/a\u003e\n  \u003cbr/\u003e\n  \u003cbr/\u003e\n  \u003cstrong\u003eAward-Factory: Awards crafted for you by a hilariously talented generative AI\u003c/strong\u003e\n  \u003cbr/\u003e\n  \u003cbr/\u003e\n  \u003ca href='https://paperswithcode.com/paper/gemma-open-models-based-on-gemini-research'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Paperswithcode-Gemma:%20Open%20Models%20Based on%20Gemini%20Research%20and%20Technology-25c2a0?style=flat-square\"/\u003e\n  \u003c/a\u003e\n  \u003cbr/\u003e\n  \u003cbr/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Next.js-000000?style=flat-square\u0026logo=nextdotjs\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/PWA-5A0FC8?style=flat-square\u0026logo=pwa\u0026logoColor=white\"/\u003e \n  \u003cimg src=\"https://img.shields.io/badge/NestJS-E0234E?style=flat-square\u0026logo=nestjs\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/FastAPI-009688?style=flat-square\u0026logo=fastapi\u0026logoColor=white\"/\u003e\n  \u003cbr/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/GraphQL-E10098?style=flat-square\u0026logo=graphql\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/MongoDB-47A248?style=flat-square\u0026logo=mongodb\u0026logoColor=white\"/\u003e\n  \u003cbr/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Docker-2496ED?style=flat-square\u0026logo=Docker\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/Jenkins-D24939?style=flat-square\u0026logo=jenkins\u0026logoColor=white\"/\u003e\n  \u003cimg src=\"https://img.shields.io/badge/AWS-232F3E?style=flat-square\u0026logo=amazonwebservices\u0026logoColor=white\"/\u003e\n\u003c/p\u003e\n\u003cbr/\u003e\n\n\u003cp align=\"center\"\u003e  \n  \u003cstrong\u003eCheck out prototypes in the badge below\u003cstrong\u003e\n  \u003cbr/\u003e\n  \u003cbr/\u003e\n  \u003ca href='https://award-factory.vercel.app'\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Website-Vercel-000000?style=flat-square\u0026logo=vercel\u0026logoColor=white\"/\u003e\n  \u003c/a\u003e\n  \u003ca href='https://huggingface.co/ziweek/gemma-2b-it-award-factory'\u003e\n      \u003cimg src=\"https://img.shields.io/badge/Model-Hugging%20Face-FFD21E?style=flat-square\u0026logo=huggingface\u0026logoColor=white\"/\u003e\n  \u003c/a\u003e\n  \u003ca href='https://huggingface.co/datasets/ziweek/award-factory-citation'\u003e\n      \u003cimg src=\"https://img.shields.io/badge/Dataset-Hugging%20Face-FFD21E?style=flat-square\u0026logo=huggingface\u0026logoColor=white\"/\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cbr/\u003e\n\u003cbr/\u003e\n\n# 1. Introduction\n\n\u003e [!NOTE]\n\u003e\n\u003e - This project aims to develop a service where anyone can effortlessly create a customized certificate in just a few minutes, making it easy to celebrate and appreciate others.\n\u003e - Award Factory was conceived as a heartwarming project to spread happiness, inspired by the idea of creating special certificates for parents. Built with sustainability in mind, the service integrates front-end components and leverages the fine-tuned Google Gemma:2b model to deliver personalized award texts. While the service is not fully active due to server operation costs, a demo is available on Huggingface.\n\u003e - Advanced technologies like QLoRA quantization and llama-cpp optimizations were employed to reduce model size and improve performance, ensuring an efficient user experience in the future.\n\nhttps://github.com/user-attachments/assets/2def17e0-46ea-4561-8b50-fc78d595b88b\n\n\u003ctable\u003e\n    \u003ctr\u003e\n    \u003ctd style=\"width:1/2;\"\u003e\n      \u003cp align=\"center\"\u003eApp Design\u003c/p\u003e\n    \u003c/td\u003e\n    \u003ctd style=\"width:1/2;\"\u003e\n      \u003cp align=\"center\"\u003eGenerated Awards\u003c/p\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"width:1/2;\"\u003e\n      \u003cimg src=\"./src/screenshots.png\"/\u003e\n    \u003c/td\u003e\n    \u003ctd style=\"width:1/2;\"\u003e\n      \u003cimg src=\"./src/results.png\"/\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\u003cbr/\u003e\n\u003cbr/\u003e\n\n# Implementation\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"width:1/2;\"\u003e\n      \u003cimg src=\"./src/diagram.png\"/\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\u003cdetails open\u003e\n \u003csummary\u003e\u003cb\u003eGoogle Gemma:2B Finetuning\u003c/b\u003e\u003c/summary\u003e\nImplemented prompt engineering and QLoRA-based quantization fine-tuning using the Google/Gemma-2b-it model with PEFT techniques to optimize personalized award text generation tailored to user preferences.\n\u003c/details\u003e\n\u003cbr/\u003e\n\n\u003cdetails open\u003e\n \u003csummary\u003e\u003cb\u003ellama-cpp Quantization\u003c/b\u003e\u003c/summary\u003e\nApplied quantization with the Q5_K_M option in llama-cpp, achieving a 63.3% reduction in model size and an 83.4% decrease in inference time without compromising performance, enabling faster and more efficient service.\n\n\u003cbr/\u003e\n\n```\n$ llama.cpp/llama-quantize gguf_model/gemma-2b-it-award-factory-v2.gguf gguf_model/gemma-2b-it-award-factory-v2.gguf-Q5_K_M.gguf Q5_K_M\n\n...\nllama_model_quantize_internal: model size  =  4780.29 MB\nllama_model_quantize_internal: quant size  =  1748.67 MB\n\nmain: quantize time = 17999.81 ms\nmain:    total time = 17999.81 ms\n```\n\n```\n$ ollama list\n\nNAME                    ID              SIZE      MODIFIED\naward-factory:q5        8df06172b64b    1.8 GB    19 seconds ago\naward-factory:latest    ae186115cc83    5.0 GB    28 minutes ago\n```\n\n\u003c/details\u003e\n\u003cbr/\u003e\n\n\u003cdetails open\u003e\n  \u003csummary\u003e\u003cb\u003eDocker-compose\u003c/b\u003e\u003c/summary\u003e\nUtilized Docker Compose to containerize the backend and frontend services, ensuring consistency in deployment environments and facilitating scalable and maintainable full-stack web application development.\n\u003c/details\u003e\n\u003cbr/\u003e\n\u003cbr/\u003e\n\n# Contribution\n\n\u003ca href=\"https://github.com/ziweek/award-factory/graphs/contributors\"\u003e\n  \u003cimg src=\"https://contrib.rocks/image?repo=ziweek/award-factory\" /\u003e\n\u003c/a\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fziweek%2Faward-factory","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fziweek%2Faward-factory","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fziweek%2Faward-factory/lists"}