Qwen2.5-3B-Instruct-math-safe

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

This model is a conservatively pruned version of Qwen/Qwen2.5-3B-Instruct.

Performance Comparison

Category	Original	Pruned	Change
Python	92.3%	92.3%	→
Html	40.0%	40.0%	→
Trivia	100.0%	100.0%	→
Math	100.0%	100.0% ⭐	→
Reasoning	91.7%	91.7%	→
Medical	64.3%	64.3%	→
Linux	69.2%	69.2%	→
Writing	54.5%	54.5%	→

Average: 76.5% → 76.5% (+0.0%)

Math Retention: 100.0%

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/Qwen2.5-3B-Instruct-math-safe")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/Qwen2.5-3B-Instruct-math-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	Qwen/Qwen2.5-3B-Instruct
Specialization	Math
Prune Mode	Safe
Weight Reduction	1% weights pruned

License

This model inherits the license from the base model.