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

🎯 PYTHON-optimized | 📦 Safe pruning | ⚡ 1% weights pruned

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

Performance Comparison

Category	Original	Pruned	Change
Python	45.0%	55.0% ⭐	↑ 10.0%
Html	67.5%	65.0%	↓ 2.5%
Trivia	92.5%	87.5%	↓ 5.0%
Math	97.5%	97.5%	→
Reasoning	97.5%	97.5%	→
Medical	65.0%	67.5%	↑ 2.5%
Linux	47.5%	47.5%	→
Writing	92.5%	92.5%	→

Average: 75.6% → 76.2% (+0.6%)

Python Retention: 122.2%

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

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

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))