EXAONE-4.0-1.2B-reasoning-aggressive

🎯 REASONING-optimized | 📦 Aggressive pruning | ⚡ 35% weights pruned

This model is a aggressively pruned version of LGAI-EXAONE/EXAONE-4.0-1.2B.

Performance Comparison

Category	Original	Pruned	Change
Python	91.7%	25.0%	↓ 66.7%
Html	58.3%	41.7%	↓ 16.7%
Trivia	91.7%	58.3%	↓ 33.3%
Math	83.3%	58.3%	↓ 25.0%
Reasoning	75.0%	41.7% ⭐	↓ 33.3%
Medical	33.3%	8.3%	↓ 25.0%
Linux	8.3%	8.3%	→
Writing	41.7%	25.0%	↓ 16.7%

Average: 60.4% → 33.3% (-27.1%)

Reasoning Retention: 55.6%

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

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

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	Reasoning
Prune Mode	Aggressive
Weight Reduction	35% weights pruned

License

This model inherits the license from the base model.