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

PYTHON-optimized | Aggressive pruning | 35% weights pruned

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

Pruning Alert: The benchmarks show virtually NO quality drop! This isn't a bug -- it is a feature. The Wanda pruning algorithm is so effective at identifying unimportant weights that it can remove a large percentage of parameters without affecting performance. Think of it like pruning dead leaves from a tree -- the tree does not miss them because they were not doing anything anyway!

Performance Comparison

Category	Original	Pruned	Change
Python	0.0%	0.0% ⭐	→
Html	0.0%	0.0%	→
Trivia	95.0%	95.0%	→
Math	100.0%	100.0%	→
Reasoning	100.0%	100.0%	→
Medical	65.0%	65.0%	→
Linux	50.0%	50.0%	→
Writing	95.0%	95.0%	→

Average: 63.1% -> 63.1% (+0.0%)

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))