README.md

---
license: apache-2.0
tags:
- pruned
- python
- optimized
base_model: LGAI-EXAONE/EXAONE-4.0-1.2B
---

# EXAONE-4.0-1.2B-python-light

This model is a **light** pruned version of [LGAI-EXAONE/EXAONE-4.0-1.2B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B), specialized for **PYTHON** tasks.

## Pruning Details

- **Base Model**: LGAI-EXAONE/EXAONE-4.0-1.2B
- **Specialization**: Python
- **Prune Mode**: Light
- **Method**: Activation-based weight pruning

## Performance Comparison

| Category | Original | Pruned |
|----------|----------|--------|
| Python | 20.0% | 20.0% |
| HTML | 6.7% | 0.0% |
| Trivia | 86.7% | N/A |
| Math | 60.0% | N/A |
| Reasoning | N/A | N/A |
| Medical | 93.3% | N/A |
| Linux | 93.3% | N/A |
| Writing | 46.7% | N/A |

![Comparison Graph](comparison_graph.png)

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/EXAONE-4.0-1.2B-python-light")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/EXAONE-4.0-1.2B-python-light")
```

## License

This model inherits the license from the base model.