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

🎯 LINUX-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	12.5%	12.5%	→
Html	25.0%	27.5%	↑ 2.5%
Trivia	97.5%	97.5%	→
Math	100.0%	100.0%	→
Reasoning	82.5%	85.0%	↑ 2.5%
Medical	95.0%	97.5%	↑ 2.5%
Linux	35.0%	32.5% ⭐	↓ 2.5%
Writing	80.0%	82.5%	↑ 2.5%

Average: 65.9% → 66.9% (+0.9%)

Linux Retention: 92.9%

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

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