|  | |
|  | |
| # Welcome to your organization's demo respository | |
| This code repository (or "repo") is designed to demonstrate the best GitHub has to offer with the least amount of noise. | |
| The repo includes an `index.html` file (so it can render a web page), two GitHub Actions workflows, and a CSS stylesheet dependency. | |
| # Model-Improvement-Platform-With-RLHF | |
| Platform being developed at MIT in collaboration with HuggingFace. Aimed at improving performance of existing Large Language Models through real time human feedback loop. | |
| # HF-RLHF-Platform | |
| Platform being developed at MIT in collaboration with HuggingFace. Aimed at improving performance of existing Large Language Models through real-time human feedback loop. | |
| This repository hosts the development of an automated RLHF platform for Hugging Face, where the community can provide real-time feedback on language models. The feedback is automatically integrated into an RLHF pipeline to continuously fine-tune and improve the models. | |
| # The Feedback Collective | |
| **Open RLHF on VLMs for Students** | |
| A community-driven project to enhance Vision-Language Models (VLMs) for student-focused tasks. | |
| Leverages feedback from users and automated RLHF pipelines to continuously improve model performance and usability. | |
| ## Dataset Schema for Project | |
| ### KTO Dataset Structure | |
| The dataset should be organized into two splits: `train` and `test`. | |
| Each split contains the following features: | |
| | **Feature** | **Type** | **Description** | | |
| |---------------|-----------|--------------------------------------------------------------------------------------| | |
| | `prompt` | `string` | The input text for the model. This should be a natural language query or input. | | |
| | `completion` | `string` | The output text generated by the model in response to the `prompt`. | | |
| | `label` | `bool` | A binary value (`True` or `False`) indicating whether the `completion` is desirable. | | |