Qwen3-1.7B-linux-medium-light

🎯 LINUX-optimized | 📦 Medium Light pruning | ⚡ 18% weights pruned

This model is a moderate-lightly pruned version of Qwen/Qwen3-1.7B, specialized for LINUX tasks using activation-aware weight pruning (Wanda-style).

✨ Key Features

• Specialization: Optimized for Linux tasks
• Pruning Method: Wanda-style (|W| × |activation|) importance scoring
• Size Reduction: 18% weights pruned
• Use Case: Noticeable compression with good performance

📊 Performance Comparison

Category	Original	Pruned	Change
Python	40.0%	60.0%	↑ 20.0%
Html	0.0%	6.7%	↑ 6.7%
Trivia	100.0%	100.0%	→
Math	100.0%	100.0%	→
Reasoning	N/A	N/A
Medical	93.3%	93.3%	→
Linux	100.0%	100.0% ⭐	→
Writing	73.3%	66.7%	↓ 6.7%

Average: 72.4% → 75.2% (+2.9%)

Linux Retention: 100.0% of original performance

🚀 Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("CompactAI/Qwen3-1.7B-linux-medium-light")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/Qwen3-1.7B-linux-medium-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/Qwen3-1.7B
Specialization	Linux
Prune Mode	Medium Light
Pruning Method	Activation-based weight pruning (Wanda)
Weight Reduction	18% weights pruned

🔗 Related Models

This model is part of the Qwen3-1.7B 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/Qwen3-1.7B.

---

Generated by ZANNPS [Zeto Automatic Neural Network Pruning System]