README.md

# MCQ_Generator_LLAMA3.2

This model is a fine-tuned version of unsloth/Llama-3.2-3B-Instruct trained on the SciQ dataset for multiple-choice question generation.

## Model Details
- Base Model: unsloth/Llama-3.2-3B-Instruct
- Training Data: SciQ dataset
- Task: Multiple Choice Question Generation
- Training Framework: Unsloth with LoRA fine-tuning

## Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kenzykhaled/MCQ_Generator_LLAMA3.2")
model = AutoModelForCausalLM.from_pretrained("kenzykhaled/MCQ_Generator_LLAMA3.2")
```

## Training Details
- LoRA rank: 16
- Training steps: 60
- Learning rate: 2e-4
- Max sequence length: 2048