Upload folder using huggingface_hub

README.md

@@ -5,7 +5,6 @@ tags:
 - html
 - optimized
 - wanda
-- activation-pruning
 base_model: Qwen/Qwen3-0.6B
 pipeline_tag: text-generation
 ---
@@ -14,35 +13,28 @@ pipeline_tag: text-generation
 
 > 🎯 **HTML-optimized** | 📦 **Safe** pruning | ⚡ **1% weights pruned**
 
-This model is a **conservatively pruned** version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B), specialized for **HTML** tasks using activation-aware weight pruning (Wanda-style).
+This model is a **conservatively pruned** version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
 
-## ✨ Key Features
-
-- **Specialization**: Optimized for Html tasks
-- **Pruning Method**: Wanda-style (|W| × |activation|) importance scoring
-- **Size Reduction**: 1% weights pruned
-- **Use Case**: High accuracy retention, ideal for production use
-
-## 📊 Performance Comparison
+## Performance Comparison
 
 | Category | Original | Pruned | Change |
 |----------|----------|--------|--------|
-| Python | 30.0% | 40.0% | ↑ 10.0% |
+| Python | 0.0% | 0.0% | → |
 | **Html** | 0.0% | 0.0% ⭐ | → |
-| Trivia | 90.0% | 90.0% | → |
-| Math | 96.7% | 93.3% | ↓ 3.3% |
-| Reasoning | 36.7% | 36.7% | → |
-| Medical | 83.3% | 86.7% | ↑ 3.3% |
-| Linux | 93.3% | 93.3% | → |
-| Writing | 53.3% | 60.0% | ↑ 6.7% |
+| Trivia | 28.6% | 28.6% | → |
+| Math | 33.3% | 33.3% | → |
+| Reasoning | 20.0% | 20.0% | → |
+| Medical | 66.7% | 66.7% | → |
+| Linux | 40.0% | 40.0% | → |
+| Writing | 16.7% | 16.7% | → |
 
-**Average**: 60.4% → 62.5% (+2.1%)
+**Average**: 25.7% → 25.7% (+0.0%)
 
 
 
 ![Comparison Graph](comparison_graph.png)
 
-## 🚀 Quick Start
+## Quick Start
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -50,31 +42,20 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 model = AutoModelForCausalLM.from_pretrained("CompactAI/Qwen3-0.6B-html-safe")
 tokenizer = AutoTokenizer.from_pretrained("CompactAI/Qwen3-0.6B-html-safe")
 
-# 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
+## Technical Details
 
 | Property | Value |
 |----------|-------|
 | Base Model | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) |
 | Specialization | Html |
 | Prune Mode | Safe |
-| Pruning Method | Activation-based weight pruning (Wanda) |
 | Weight Reduction | 1% weights pruned |
 
-## 🔗 Related Models
-
-This model is part of the **Qwen3-0.6B** pruned model collection. Variants:
-- **Safe** - Conservative pruning (~10-20%), high accuracy retention
-- **Aggressive** - Maximum compression (~40-50%), best for edge deployment
+## License
 
-## 📜 License
-
-This model inherits the license from the base model [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
-
----
-*Generated by ZANNPS [Zeto Automatic Neural Network Pruning System]*
+This model inherits the license from the base model.

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac42828b0df838ff64948a77496fdd08c2b7a6e097ec6cd514db348c76d0fcd
+oid sha256:ef9fcca52692b642e0f789180f6132e343b22bf19f45041240b41945ac250d1e
 size 1503300016

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fea4f89c198c65a418ebfd87d7480db83fe21f31c7f56cd2ecea1110b1dff53e
+oid sha256:bb5aa816bcb7fb495b5269f933d2710c6170d4dd410f5010a21bbfdd8c41f963
 size 11422917