Qwen2.5-0.5B-python-aggressive

🎯 PYTHON-optimized | 📦 Aggressive pruning | ⚡ 1% weights pruned

This model is a aggressively pruned version of Qwen/Qwen2.5-0.5B.

Performance Comparison

Category	Original	Pruned	Change
Python	0.0%	0.0% ⭐	→
Html	0.0%	0.0%	→
Trivia	64.3%	64.3%	→
Math	73.3%	73.3%	→
Reasoning	80.0%	80.0%	→
Medical	83.3%	83.3%	→
Linux	60.0%	60.0%	→
Writing	50.0%	33.3%	↓ 16.7%

Average: 51.4% → 49.3% (-2.1%)

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/Qwen2.5-0.5B-python-aggressive")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/Qwen2.5-0.5B-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))

Technical Details

Property	Value
Base Model	Qwen/Qwen2.5-0.5B
Specialization	Python
Prune Mode	Aggressive
Weight Reduction	1% weights pruned

License

This model inherits the license from the base model.