Spaces:
Running
Running
| title: README | |
| emoji: 🚀 | |
| colorFrom: green | |
| colorTo: pink | |
| sdk: static | |
| pinned: true | |
| license: apache-2.0 | |
| thumbnail: >- | |
| https://cdn-uploads.huggingface.co/production/uploads/679be80366c379e2159c7ba3/mqNQ14axq9eAnIRk0dt3C.png | |
| short_description: Hub for Distilled Open Source LLMs | |
| tags: | |
| - edge-ai | |
| - llm-fine-tuning | |
| - knowledge-distillation | |
| - peft | |
| - kaggle | |
| - tpu | |
| - gpu | |
| # Welcome to the Sweelol AI Hub! 🚀 | |
| ## Our Mission | |
| The future of **AI is personal**. At **SweeLOL ai**, we are on that mission. | |
| We are an open-source research hub dedicated to creating **"Personal LLMs"** compact, powerful, and specialized models designed to run on the devices you use every day. | |
| Our mission is to democratize state-of-the-art AI for **Edge** and resource-constrained environments. | |
| Explore our library of models, our groundbreaking benchmark results, and the battle-tested **Kaggle TPU & GPU** templates we used to build them. | |
| ## About the Author | |
| This project was led by **SweeLOL**, an AI researcher and engineer passionate about making powerful AI accessible. | |
| * **[Swee.LOL](https://swee.lol/page.html)** | |
| * **[Kaggle Profile](https://www.kaggle.com/sweelol)** | |
| * **[GitHub Profile](https://github.com/sweelol)** | |