LFM2.5-1.2B-Instruct-reasoning-safe

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

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

Performance Comparison

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

Average: 64.6% → 64.6% (+0.0%)

Reasoning Retention: 100.0%

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

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

Technical Details

Property	Value
Base Model	LiquidAI/LFM2.5-1.2B-Instruct
Specialization	Reasoning
Prune Mode	Safe
Weight Reduction	1% weights pruned

License

This model inherits the license from the base model.