LFM2.5-1.2B-Thinking-python-aggressive

🎯 PYTHON-optimized | 📦 Aggressive pruning | ⚡ 30% weights pruned

This model is a aggressively pruned version of LiquidAI/LFM2.5-1.2B-Thinking.

Performance Comparison

Category	Original	Pruned	Change
Python	45.0%	12.5% ⭐	↓ 32.5%
Html	67.5%	7.5%	↓ 60.0%
Trivia	92.5%	80.0%	↓ 12.5%
Math	97.5%	97.5%	→
Reasoning	97.5%	87.5%	↓ 10.0%
Medical	65.0%	40.0%	↓ 25.0%
Linux	47.5%	35.0%	↓ 12.5%
Writing	92.5%	40.0%	↓ 52.5%

Average: 75.6% → 50.0% (-25.6%)

Python Retention: 27.8%

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/LFM2.5-1.2B-Thinking-python-aggressive")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/LFM2.5-1.2B-Thinking-python-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))