EXAONE-4.0-1.2B-medical-aggressive

🎯 MEDICAL-optimized | 📦 Aggressive pruning | ⚡ 25% weights pruned

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

Performance Comparison

Category	Original	Pruned	Change
Python	76.9%	69.2%	↓ 7.7%
Html	20.0%	40.0%	↑ 20.0%
Trivia	86.7%	60.0%	↓ 26.7%
Math	80.0%	80.0%	→
Reasoning	75.0%	58.3%	↓ 16.7%
Medical	42.9%	35.7% ⭐	↓ 7.1%
Linux	23.1%	38.5%	↑ 15.4%
Writing	54.5%	36.4%	↓ 18.2%

Average: 57.4% → 52.3% (-5.1%)

Medical Retention: 83.3%

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/EXAONE-4.0-1.2B-medical-aggressive")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/EXAONE-4.0-1.2B-medical-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	Medical
Prune Mode	Aggressive
Weight Reduction	25% weights pruned

License

This model inherits the license from the base model.