https://github.com/mrigank005/rubric_generator
This repository contains a machine learning model designed to generate grading rubrics based on a given question and a sample answer. The model has been fine-tuned on custom data and implemented in a Jupyter Notebook.
https://github.com/mrigank005/rubric_generator
Last synced: about 1 month ago
JSON representation
This repository contains a machine learning model designed to generate grading rubrics based on a given question and a sample answer. The model has been fine-tuned on custom data and implemented in a Jupyter Notebook.
- Host: GitHub
- URL: https://github.com/mrigank005/rubric_generator
- Owner: Mrigank005
- License: mit
- Created: 2025-05-02T22:25:27.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-02T22:27:59.000Z (about 1 year ago)
- Last Synced: 2025-05-13T20:28:23.626Z (about 1 year ago)
- Language: Jupyter Notebook
- Homepage: https://huggingface.co/Mrigank005/Rubric_Generator
- Size: 43 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# Rubric Generator using Fine-Tuned ML Model
This repository contains a machine learning model designed to **generate grading rubrics** based on a given question and a sample answer. The model has been fine-tuned on custom data and implemented in a Jupyter Notebook.
## 📁 Repository Structure
- `rubric_generator.ipynb`: Jupyter notebook containing the code to load and use the fine-tuned model to generate rubrics.
- `converted_finetune_rubric_data.txt`: Text file containing the data used to fine-tune the model. This file follows the format required for supervised fine-tuning (e.g., question-answer pairs with associated rubric).
## 🧠 Model Functionality
The model takes two inputs:
1. **Question** – The original question or prompt for which a rubric is needed.
2. **Sample Answer** – A sample response to the question.
Based on this input, it outputs a **detailed rubric** that can be used for evaluation or instructional purposes.
## 🚀 Getting Started
### Prerequisites
- Python 3.7+
- Jupyter Notebook
- OpenAI or HuggingFace-compatible ML libraries (e.g., `transformers`, `openai`, etc.)
- `pandas`, `json`, or any required dependencies (see the notebook for details)
### Running the Notebook
1. Clone the repository:
```bash
git clone https://github.com/yourusername/rubric-generator.git
cd rubric-generator
````
2. Open the notebook:
```bash
jupyter notebook rubric_generator.ipynb
```
3. Run the cells to load the model and generate a rubric based on your input.
## 📊 Fine-Tuning Data
The file `converted_finetune_rubric_data.txt` contains the dataset used for fine-tuning the model. This data includes:
* Structured examples of questions,
* Sample answers,
* Corresponding rubrics.
## 📄 License
This project is licensed under the [MIT License](LICENSE).
---
**Author**: Mrigank Singh
**Contact**: Mriganksingh005@gmail.com