metadata
license: apache-2.0
tags:
- pruned
- python
- optimized
- wanda
- activation-pruning
base_model: LGAI-EXAONE/EXAONE-4.0-1.2B
pipeline_tag: text-generation
EXAONE-4.0-1.2B-python-medium-heavy
🎯 PYTHON-optimized | 📦 Medium Heavy pruning | ⚡ 10% weights pruned
This model is a moderate-heavyly pruned version of LGAI-EXAONE/EXAONE-4.0-1.2B, specialized for PYTHON tasks using activation-aware weight pruning (Wanda-style).
✨ Key Features
- Specialization: Optimized for Python tasks
- Pruning Method: Wanda-style (|W| × |activation|) importance scoring
- Size Reduction: 10% weights pruned
- Use Case: Significant compression, some accuracy trade-off
📊 Performance Comparison
| Category | Original | Pruned | Change |
|---|---|---|---|
| Python | 20.0% | 20.0% ⭐ | → |
| Html | 6.7% | 6.7% | → |
| Trivia | 86.7% | 93.3% | ↑ 6.7% |
| Math | 60.0% | 53.3% | ↓ 6.7% |
| Reasoning | N/A | N/A | |
| Medical | 93.3% | 93.3% | → |
| Linux | 93.3% | 93.3% | → |
| Writing | 46.7% | 46.7% | → |
Average: 58.1% → 58.1% (-0.0%)
Python Retention: 100.0% of original performance
🚀 Quick Start
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("CompactAI/EXAONE-4.0-1.2B-python-medium-heavy")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/EXAONE-4.0-1.2B-python-medium-heavy")
# Example usage
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 |
| Specialization | Python |
| Prune Mode | Medium Heavy |
| Pruning Method | Activation-based weight pruning (Wanda) |
| Weight Reduction | 10% weights pruned |
🔗 Related Models
This model is part of the EXAONE-4.0-1.2B pruned model collection. Other variants:
- Extra-light (minimal pruning)
- Light
- Medium-light
- Medium
- Medium-heavy
- Heavy
- Extra-heavy (maximum compression)
📜 License
This model inherits the license from the base model LGAI-EXAONE/EXAONE-4.0-1.2B.
Generated by ZANNPS [Zeto Automatic Neural Network Pruning System]