{"id":21298884,"url":"https://github.com/rathod-shubham/finetuning-llms","last_synced_at":"2026-05-07T18:32:06.736Z","repository":{"id":261185158,"uuid":"883529166","full_name":"RATHOD-SHUBHAM/Finetuning-LLMs","owner":"RATHOD-SHUBHAM","description":"This repository contains experiments on fine-tuning LLMs (Llama, Llama3.1, Gemma). It includes notebooks for model tuning, data preprocessing, and hyperparameter optimization to enhance model performance.","archived":false,"fork":false,"pushed_at":"2025-05-05T00:56:16.000Z","size":6570,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-03T23:33:21.578Z","etag":null,"topics":["adapter","colab-notebook","dpo","fine-tuning","gemma","huggingface","llama","llm","lora","peft-fine-tuning-llm","python","qlora","stf","transformer","unsloth"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RATHOD-SHUBHAM.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2024-11-05T05:57:49.000Z","updated_at":"2025-05-05T00:56:20.000Z","dependencies_parsed_at":"2024-11-05T06:33:36.304Z","dependency_job_id":"440397c3-e961-48c2-b648-ff4ab6d1c843","html_url":"https://github.com/RATHOD-SHUBHAM/Finetuning-LLMs","commit_stats":null,"previous_names":["rathod-shubham/finetuning-llms"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/RATHOD-SHUBHAM/Finetuning-LLMs","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RATHOD-SHUBHAM%2FFinetuning-LLMs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RATHOD-SHUBHAM%2FFinetuning-LLMs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RATHOD-SHUBHAM%2FFinetuning-LLMs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RATHOD-SHUBHAM%2FFinetuning-LLMs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RATHOD-SHUBHAM","download_url":"https://codeload.github.com/RATHOD-SHUBHAM/Finetuning-LLMs/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RATHOD-SHUBHAM%2FFinetuning-LLMs/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32750477,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-07T02:14:30.463Z","status":"ssl_error","status_checked_at":"2026-05-07T02:14:29.405Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: 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":["adapter","colab-notebook","dpo","fine-tuning","gemma","huggingface","llama","llm","lora","peft-fine-tuning-llm","python","qlora","stf","transformer","unsloth"],"created_at":"2024-11-21T14:58:16.420Z","updated_at":"2026-05-07T18:32:06.691Z","avatar_url":"https://github.com/RATHOD-SHUBHAM.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Fine-Tuning LLMs: Experimental Repository\nWelcome to this repository where I explore fine-tuning various Large Language Models (LLMs). This repository contains my experiments with fine-tuning LLMs for different use cases and tasks. The project is intended to help understand how different configurations and datasets affect model performance.\n\n## Repository Structure\nThe repository is organized into multiple folders, each corresponding to a different fine-tuning experiment. Below is an overview of the directory structure:\n\n```\n/llama3                  # Llama 3 model fine-tuning notebooks\n/llama3.1                # Llama 3.1 model fine-tuning notebooks\n/gemma                   # Gemma model fine-tuning notebooks\n/data_preprocessing      # Scripts and notebooks to format and preprocess data for fine-tuning\n```\n\n## Folders:\n1. Llama:\n* /llama3\n  Contains notebooks focused on fine-tuning the Llama 3 model. Each notebook in this folder explores different techniques, hyperparameters, and strategies for improving the performance of the model.\n\n* /llama3.1\n  Contains experiments with the Llama 3.1 model. This folder might have updated methods or adjustments compared to Llama 3 fine-tuning strategies.\n\n2. Gemma\nIncludes experiments involving the Gemma model. Here, I attempt fine-tuning with different datasets and configurations.\n\n3. Data Preprocessing\nThis folder contains code for preparing and formatting the dataset to be compatible with the fine-tuning process. It includes scripts for data cleaning, tokenization, and ensuring the right format for the LLMs.\n\n## Purpose\nThis repository is meant to document my experiments with LLM fine-tuning to better understand the nuances of model training and optimization. The primary goal is to experiment with different configurations and gain insights into how different models react to various training strategies.\n\n## Getting Started\n### Prerequisites\n* Python 3.x\n* Jupyter Notebook (for running the notebooks)\n\n### Installation\nClone the repository to your local machine:\n```\ngit clone https://github.com/your-username/llm-finetuning-experiments.git\n```\n\nNavigate to the repository directory:\n```\ncd llm-finetuning-experiments\n```\n\nRunning the Notebooks\nTo explore the fine-tuning experiments, you can open the Jupyter Notebooks in each model-specific folder. For example:\n```\njupyter notebook llama3/finetuning_notebook.ipynb\n```\n\n## Notes\nThis repository is intended for my personal understanding of LLM fine-tuning, and the experiments may not be fully optimized or production-ready.\nFeel free to explore, adapt, and experiment further, though keep in mind this is an experimental setup.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frathod-shubham%2Ffinetuning-llms","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frathod-shubham%2Ffinetuning-llms","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frathod-shubham%2Ffinetuning-llms/lists"}