{"id":25764781,"url":"https://github.com/codeofrahul/fine_tuning_gemma_model","last_synced_at":"2025-08-19T19:22:10.152Z","repository":{"id":278528732,"uuid":"935915862","full_name":"CodeofRahul/Fine_Tuning_Gemma_Model","owner":"CodeofRahul","description":"This project demonstrates how to fine-tune the Gemma-2B language model for conversation summarization using QLoRA (Quantized Low-Rank Adaptation) on the SAMSum dataset. It leverages Hugging Face Transformers, PEFT, and BitsAndBytes libraries for efficient and effective fine-tuning.","archived":false,"fork":false,"pushed_at":"2025-02-20T08:32:18.000Z","size":42,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-08T13:12:14.076Z","etag":null,"topics":["finetuning-large-language-models","finetuning-llms","gemma-2b","huggingface"],"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/CodeofRahul.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":"2025-02-20T08:23:12.000Z","updated_at":"2025-02-20T08:35:54.000Z","dependencies_parsed_at":"2025-02-20T09:43:16.006Z","dependency_job_id":null,"html_url":"https://github.com/CodeofRahul/Fine_Tuning_Gemma_Model","commit_stats":null,"previous_names":["codeofrahul/fine_tuning_gemma_model"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CodeofRahul/Fine_Tuning_Gemma_Model","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FFine_Tuning_Gemma_Model","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FFine_Tuning_Gemma_Model/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FFine_Tuning_Gemma_Model/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FFine_Tuning_Gemma_Model/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CodeofRahul","download_url":"https://codeload.github.com/CodeofRahul/Fine_Tuning_Gemma_Model/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FFine_Tuning_Gemma_Model/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271206993,"owners_count":24718705,"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","status":"online","status_checked_at":"2025-08-19T02:00:09.176Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["finetuning-large-language-models","finetuning-llms","gemma-2b","huggingface"],"created_at":"2025-02-26T21:26:45.257Z","updated_at":"2025-08-19T19:22:10.082Z","avatar_url":"https://github.com/CodeofRahul.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Gemma-2B Fine-tuned for Summarization using QLoRA\n\nThis project demonstrates how to fine-tune the Gemma-2B language model for conversation summarization using QLoRA (Quantized Low-Rank Adaptation) on the SAMSum dataset. It leverages Hugging Face Transformers, PEFT, and BitsAndBytes libraries for efficient and effective fine-tuning.\n\n## Project Overview\n\nThe goal of this project is to create a model capable of generating concise and accurate summaries of conversations. We achieve this by fine-tuning a pre-trained Gemma-2B model using QLoRA, a technique that reduces memory footprint and speeds up training while maintaining performance. The SAMSum dataset, consisting of dialogues and their corresponding summaries, is used for training and evaluation.\n\n## Key Features\n\n- **Fine-tuning Gemma-2B:** Leverages the powerful Gemma-2B language model as the foundation.\n- **QLoRA for Efficiency:** Employs Quantized Low-Rank Adaptation for memory-efficient fine-tuning.\n- **SAMSum Dataset:** Utilizes a well-established dataset for conversation summarization.\n- **Hugging Face Ecosystem:** Integrates seamlessly with Hugging Face Transformers, PEFT, and Datasets libraries.\n- **Detailed Code:** Provides clear and well-commented code for easy understanding and reproducibility.\n\n## Getting Started\n\n1. **Clone the repository:**\n2. **Install dependencies:**\n3. **Authenticate with Hugging Face Hub:**\n\n4. **Run the Colab notebook:**\n   Open the notebook in Google Colab and execute the cells. This will download the dataset, fine-tune the model, and save the results.\n\n## Usage\n\nAfter fine-tuning, you can use the model to generate summaries of conversations:\n\n## Results\n\nThe fine-tuned model achieves promising results on the SAMSum dataset, demonstrating its ability to generate informative and concise summaries.\n\n## Contributing\n\nContributions are welcome! If you find any issues or have suggestions for improvements, please feel free to open an issue or submit a pull request.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodeofrahul%2Ffine_tuning_gemma_model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodeofrahul%2Ffine_tuning_gemma_model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodeofrahul%2Ffine_tuning_gemma_model/lists"}