egyptian-mcq-generator-mistral-7b/README.md

---
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: transformers
pipeline_tag: text-generation
language:
- en
tags:
- mistral
- instruction-tuned
- lora
- unsloth
- education
- english
- mcq
- egyptian-ministry
---

# Egyptian MCQ Generator - Mistral 7B Instruct

This repository contains a LoRA fine-tuned version of **mistralai/Mistral-7B-Instruct-v0.3** for generating English multiple-choice questions that follow the official Egyptian Ministry of Education examination style.

## Model Information

- Base Model: mistralai/Mistral-7B-Instruct-v0.3
- Fine-tuning: LoRA (PEFT)
- Framework: Unsloth
- Language: English
- Task: Instruction Fine-Tuning

## Training Configuration

| Parameter | Value |
|-----------|-------|
| LoRA Rank | 16 |
| LoRA Alpha | 32 |
| Dropout | 0.05 |
| Learning Rate | 1e-4 |
| Epochs | 3 |
| Max Sequence Length | 2048 |

## Example

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "tokhey/egyptian-mcq-generator-mistral-7b"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto",
)

messages = [
    {
        "role": "system",
        "content": (
            "You are a Senior English Assessment Specialist. "
            "Generate official Egyptian Ministry of Education English MCQs. "
            "Return valid JSON only."
        ),
    },
    {
        "role": "user",
        "content": (
            "Generate 10 official Egyptian Ministry English MCQs "
            "about Past Perfect / Past Perfect Continuous."
        ),
    },
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)

inputs = tokenizer(
    text,
    return_tensors="pt",
).to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=1500,
    temperature=0.7,
)

print(
    tokenizer.decode(
        outputs[0][inputs.input_ids.shape[1]:],
        skip_special_tokens=True,
    )
)
```

## Output Format

```json
{
    "statement": "...",
    "correct_answer": "...",
    "plausible_distractors": [
        "...",
        "...",
        "..."
    ],
    "explanation": "..."
}
```

## License

This model is derived from **mistralai/Mistral-7B-Instruct-v0.3** and follows the original Mistral model license.