{"id":26977124,"url":"https://github.com/atomostechhq/google-gemma-for-web-exp","last_synced_at":"2025-04-09T15:51:19.669Z","repository":{"id":285866709,"uuid":"959605205","full_name":"atomostechhq/google-gemma-for-web-exp","owner":"atomostechhq","description":"A web-based implementation of Google's Gemma language model using MediaPipe Tasks for GenAI.","archived":false,"fork":false,"pushed_at":"2025-04-03T04:59:21.000Z","size":5,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-04-03T05:19:36.917Z","etag":null,"topics":["gemma","gen-ai","google-deepmind","llm"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","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/atomostechhq.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}},"created_at":"2025-04-03T04:00:30.000Z","updated_at":"2025-04-03T04:59:24.000Z","dependencies_parsed_at":"2025-04-03T05:19:40.553Z","dependency_job_id":null,"html_url":"https://github.com/atomostechhq/google-gemma-for-web-exp","commit_stats":null,"previous_names":["atomostechhq/google-gemma-for-web-exp"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomostechhq%2Fgoogle-gemma-for-web-exp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomostechhq%2Fgoogle-gemma-for-web-exp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomostechhq%2Fgoogle-gemma-for-web-exp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/atomostechhq%2Fgoogle-gemma-for-web-exp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/atomostechhq","download_url":"https://codeload.github.com/atomostechhq/google-gemma-for-web-exp/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248063950,"owners_count":21041854,"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":["gemma","gen-ai","google-deepmind","llm"],"created_at":"2025-04-03T12:18:21.848Z","updated_at":"2025-04-09T15:51:19.646Z","avatar_url":"https://github.com/atomostechhq.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Google Gemma for Web\n\nA web-based implementation of Google's Gemma language model using MediaPipe Tasks for GenAI.\n\n## Overview\n\nThis project demonstrates how to run Google's Gemma language model directly in the browser using WebAssembly. It provides a simple interface for text generation using the Gemma 2B model.\n\n## Features\n\n- Browser-based inference using WebAssembly\n- No server required - runs completely client-side\n- Simple text input interface\n- Real-time text generation\n\n## Prerequisites\n\n- Modern web browser with WebAssembly support\n- Kaggle account (for model download)\n\n## Setup Instructions\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/atomostechhq/google-gemma-for-web-exp.git\n   cd google-gemma-for-web-exp\n   ```\n\n2. Download the model:\n   - Follow the instructions in `assets/instructions.txt` to:\n     - Set up Kaggle authentication\n     - Download the model file\n     - Place it in the correct location\n\n3. Serve the application:\n   - Use any HTTP server to serve the files locally\n   - For example, with Python:\n     ```bash\n     python3 -m http.server 8000\n     ```\n   - Or with Node.js:\n     ```bash\n     npx http-server\n     ```\n\n4. Access the application:\n   - Open your browser and navigate to `http://localhost:8000`\n\n## Usage\n\n1. Enter your text prompt in the input field\n2. Click \"Get Response\" to generate text\n3. The model will stream its response in real-time\n\n## Technical Details\n\n- Uses MediaPipe Tasks for GenAI\n- Implements the Gemma 2B model quantized to INT8\n- Runs inference directly in the browser using WebAssembly\n\n## Limitations\n\n- Initial model loading may take some time depending on your internet connection\n- Performance depends on your device's capabilities\n\n## License\n\nThis project uses Google's Gemma model which is subject to its own license terms. Please refer to the Gemma documentation for details.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatomostechhq%2Fgoogle-gemma-for-web-exp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fatomostechhq%2Fgoogle-gemma-for-web-exp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fatomostechhq%2Fgoogle-gemma-for-web-exp/lists"}