EXAONE-4.0-1.2B-math-medium

🎯 MATH-optimized | 📦 Medium pruning | ⚡ 12% weights pruned

This model is a moderately pruned version of LGAI-EXAONE/EXAONE-4.0-1.2B, specialized for MATH tasks using activation-aware weight pruning (Wanda-style).

✨ Key Features

• Specialization: Optimized for Math tasks
• Pruning Method: Wanda-style (|W| × |activation|) importance scoring
• Size Reduction: 12% weights pruned
• Use Case: Balanced trade-off between size and accuracy

📊 Performance Comparison

Category	Original	Pruned	Change
Python	20.0%	40.0%	↑ 20.0%
Html	6.7%	6.7%	→
Trivia	86.7%	80.0%	↓ 6.7%
Math	60.0%	60.0% ⭐	→
Reasoning	N/A	N/A
Medical	93.3%	80.0%	↓ 13.3%
Linux	93.3%	93.3%	→
Writing	46.7%	40.0%	↓ 6.7%

Average: 58.1% → 57.1% (-1.0%)

Math Retention: 100.0% of original performance

🚀 Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

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

# 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	Math
Prune Mode	Medium
Pruning Method	Activation-based weight pruning (Wanda)
Weight Reduction	12% 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]