LFM2.5-1.2B-Instruct-math-aggressive

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

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

Performance Comparison

Category	Original	Pruned	Change
Python	50.0%	58.3%	↑ 8.3%
Html	83.3%	41.7%	↓ 41.7%
Trivia	91.7%	58.3%	↓ 33.3%
Math	100.0%	83.3% ⭐	↓ 16.7%
Reasoning	66.7%	33.3%	↓ 33.3%
Medical	75.0%	41.7%	↓ 33.3%
Linux	16.7%	16.7%	→
Writing	33.3%	83.3%	↑ 50.0%

Average: 64.6% → 52.1% (-12.5%)

Math Retention: 83.3%

$Comparison Graph$

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

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