Upload folder using huggingface_hub

README.md

@@ -5,44 +5,36 @@ tags:
 - html
 - optimized
 - wanda
-- activation-pruning
 base_model: Qwen/Qwen2.5-3B-Instruct
 pipeline_tag: text-generation
 ---
 
 # Qwen2.5-3B-Instruct-html-aggressive
 
-> 🎯 **HTML-optimized** | 📦 **Aggressive** pruning | ⚡ **12% weights pruned**
+> 🎯 **HTML-optimized** | 📦 **Aggressive** pruning | ⚡ **35% weights pruned**
 
-This model is a **aggressively pruned** version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct), specialized for **HTML** tasks using activation-aware weight pruning (Wanda-style).
+This model is a **aggressively pruned** version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
 
-## ✨ Key Features
-
-- **Specialization**: Optimized for Html tasks
-- **Pruning Method**: Wanda-style (|W| × |activation|) importance scoring
-- **Size Reduction**: 12% weights pruned
-- **Use Case**: Maximum compression for edge deployment
-
-## 📊 Performance Comparison
+## Performance Comparison
 
 | Category | Original | Pruned | Change |
 |----------|----------|--------|--------|
-| Python | 100.0% | 100.0% | → |
-| **Html** | 6.7% | 6.7% ⭐ | → |
-| Trivia | 66.7% | 73.3% | ↑ 6.7% |
-| Math | 60.0% | 60.0% | → |
-| Reasoning | 100.0% | 100.0% | → |
-| Medical | 86.7% | 80.0% | ↓ 6.7% |
-| Linux | 100.0% | 100.0% | → |
-| Writing | 73.3% | 80.0% | ↑ 6.7% |
+| Python | 92.3% | 69.2% | ↓ 23.1% |
+| **Html** | 40.0% | 50.0% ⭐ | ↑ 10.0% |
+| Trivia | 100.0% | 100.0% | → |
+| Math | 100.0% | 100.0% | → |
+| Reasoning | 91.7% | 91.7% | → |
+| Medical | 64.3% | 42.9% | ↓ 21.4% |
+| Linux | 69.2% | 61.5% | ↓ 7.7% |
+| Writing | 54.5% | 54.5% | → |
 
-**Average**: 74.2% → 75.0% (+0.8%)
+**Average**: 76.5% → 71.2% (-5.3%)
 
-**Html Retention**: 100.0% of original performance
+**Html Retention**: 125.0%
 
 ![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/Qwen2.5-3B-Instruct-html-aggressive")
 tokenizer = AutoTokenizer.from_pretrained("CompactAI/Qwen2.5-3B-Instruct-html-aggressive")
 
-# 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/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) |
 | Specialization | Html |
 | Prune Mode | Aggressive |
-| Pruning Method | Activation-based weight pruning (Wanda) |
-| Weight Reduction | 12% weights pruned |
-
-## 🔗 Related Models
+| Weight Reduction | 35% weights pruned |
 
-This model is part of the **Qwen2.5-3B-Instruct** 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/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
-
----
-*Generated by ZANNPS [Zeto Automatic Neural Network Pruning System]*
+This model inherits the license from the base model.

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc78dc4ea1bc4903bb47224fe427d99ee59cc53d8b9cfd09dd6aa5cc8182ade
+oid sha256:33b7e298701e525d76ae72f59be40f84d42a2bc0837740e1d990396e5ccdc682
 size 3995916600

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46db99aad28ece5a1f3916bfb48df223aa1b1127910f0d649c76143a59a31df5
+oid sha256:2ab13e2686f533d363b54fddbcf2dec947296329e1ae06f407fc124a6081b346
 size 2176009944

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51354673edf4300eb841665e1fb684cc1badea87c49d5de6ef09981151683508
+oid sha256:7b3e3adf18710ac3bd97b384b0d01b58205c4c5cd37c6c56d24c8fff86b0561d
 size 11422159