Qwen2.5-3B-Instruct-python-extra-light

🎯 PYTHON-optimized | 📦 Extra Light pruning | ⚡ 2% weights pruned

This model is a minimally pruned version of Qwen/Qwen2.5-3B-Instruct, specialized for PYTHON tasks using activation-aware weight pruning (Wanda-style).

✨ Key Features

• Specialization: Optimized for Python tasks
• Pruning Method: Wanda-style (|W| × |activation|) importance scoring
• Size Reduction: 2% weights pruned
• Use Case: Highest accuracy retention with slight size reduction

📊 Performance Comparison

Category	Original	Pruned	Change
Python	100.0%	100.0% ⭐	→
Html	6.7%	6.7%	→
Trivia	100.0%	100.0%	→
Math	60.0%	60.0%	→
Reasoning	N/A	N/A
Medical	100.0%	100.0%	→
Linux	100.0%	100.0%	→
Writing	73.3%	73.3%	→

Average: 77.1% → 77.1% (+0.0%)

Python Retention: 100.0% of original performance

🚀 Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/Qwen2.5-3B-Instruct-python-extra-light")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/Qwen2.5-3B-Instruct-python-extra-light")

# Example usage
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	Python
Prune Mode	Extra Light
Pruning Method	Activation-based weight pruning (Wanda)
Weight Reduction	2% weights pruned

🔗 Related Models

This model is part of the Qwen2.5-3B-Instruct pruned model collection. Other variants:

• Extra-light (minimal pruning)
• Light
• Medium-light
• Medium
• Medium-heavy
• Heavy
• Extra-heavy (maximum compression)

📜 License

This model inherits the license from the base model Qwen/Qwen2.5-3B-Instruct.

---

Generated by ZANNPS [Zeto Automatic Neural Network Pruning System]