Qwen3-4B
Collection
Collection of pruned models based on Qwen/Qwen3-4B
•
15 items
•
Updated
Qwen3-4B-math-heavy-prune
This model is a heavy pruned version of Qwen/Qwen3-4B, specialized for MATH tasks.
Pruning Details
- Base Model: Qwen/Qwen3-4B
- Specialization: Math
- Prune Mode: Heavy
- Method: Activation-based weight pruning
Performance Comparison
| Category | Original | Pruned |
|---|---|---|
| Python | 0.0% | 0.0% |
| HTML | 6.7% | 26.7% |
| Trivia | 86.7% | 86.7% |
| Math | 40.0% | 53.3% |
| Reasoning | 60.0% | 53.3% |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("CompactAI/Qwen3-4B-math-heavy-prune-prune")
tokenizer = AutoTokenizer.from_pretrained("CompactAI/Qwen3-4B-math-heavy-prune-prune")
License
This model inherits the license from the base model.
- Downloads last month
- 8
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support