Qwen3-0.6B
Collection
Collection of pruned models based on Qwen3-0.6B
•
16 items
•
Updated
Qwen3-0.6B-html-aggressive
🎯 HTML-optimized | 📦 Aggressive pruning | ⚡ 1% weights pruned
This model is a aggressively pruned version of Qwen/Qwen3-0.6B.
Performance Comparison
| Category | Original | Pruned | Change |
|---|---|---|---|
| Python | 0.0% | 0.0% | → |
| Html | 0.0% | 0.0% ⭐ | → |
| Trivia | 28.6% | 28.6% | → |
| Math | 33.3% | 26.7% | ↓ 6.7% |
| Reasoning | 20.0% | 20.0% | → |
| Medical | 66.7% | 66.7% | → |
| Linux | 40.0% | 40.0% | → |
| Writing | 16.7% | 16.7% | → |
Average: 25.7% → 24.8% (-0.8%)
Quick Start
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("CompactAI/Qwen3-0.6B-html-aggressive")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/Qwen3-0.6B-html-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/Qwen3-0.6B |
| Specialization | Html |
| Prune Mode | Aggressive |
| Weight Reduction | 1% weights pruned |
License
This model inherits the license from the base model.
- Downloads last month
- 10