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

# EXAONE-4.0-1.2B-python-safe

> 🎯 **PYTHON-optimized** | 📦 **Safe** pruning | ⚡ **1% weights pruned**

This model is a **conservatively pruned** version of [LGAI-EXAONE/EXAONE-4.0-1.2B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B).

## Performance Comparison

| Category | Original | Pruned | Change |
|----------|----------|--------|--------|
| **Python** | 76.9% | 76.9% ⭐ | → |
| Html | 20.0% | 20.0% | → |
| Trivia | 86.7% | 86.7% | → |
| Math | 80.0% | 80.0% | → |
| Reasoning | 75.0% | 75.0% | → |
| Medical | 42.9% | 42.9% | → |
| Linux | 23.1% | 23.1% | → |
| Writing | 54.5% | 45.5% | ↓ 9.1% |

**Average**: 57.4% → 56.2% (-1.1%)

**Python Retention**: 100.0%

![Comparison Graph](comparison_graph.png)

## Quick Start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

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

inputs = tokenizer("Your prompt here", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Technical Details

| Property | Value |
|----------|-------|
| Base Model | [LGAI-EXAONE/EXAONE-4.0-1.2B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B) |
| Specialization | Python |
| Prune Mode | Safe |
| Weight Reduction | 1% weights pruned |

## License

This model inherits the license from the base model.