Upload folder using huggingface_hub

README.md

@@ -5,44 +5,36 @@ tags:
 - python
 - optimized
 - wanda
-- activation-pruning
 base_model: LGAI-EXAONE/EXAONE-4.0-1.2B
 pipeline_tag: text-generation
 ---
 
 # EXAONE-4.0-1.2B-python-aggressive
 
-> 🎯 **PYTHON-optimized** | 📦 **Aggressive** pruning | ⚡ **7% weights pruned**
+> 🎯 **PYTHON-optimized** | 📦 **Aggressive** pruning | ⚡ **30% weights pruned**
 
-This model is a **aggressively pruned** version of [LGAI-EXAONE/EXAONE-4.0-1.2B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B), specialized for **PYTHON** tasks using activation-aware weight pruning (Wanda-style).
+This model is a **aggressively pruned** version of [LGAI-EXAONE/EXAONE-4.0-1.2B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B).
 
-## ✨ Key Features
-
-- **Specialization**: Optimized for Python tasks
-- **Pruning Method**: Wanda-style (|W| × |activation|) importance scoring
-- **Size Reduction**: 7% weights pruned
-- **Use Case**: Maximum compression for edge deployment
-
-## 📊 Performance Comparison
+## Performance Comparison
 
 | Category | Original | Pruned | Change |
 |----------|----------|--------|--------|
-| **Python** | 20.0% | 20.0% ⭐ | → |
-| Html | 6.7% | 6.7% | → |
-| Trivia | 26.7% | 53.3% | ↑ 26.7% |
-| Math | 60.0% | 53.3% | ↓ 6.7% |
-| Reasoning | 60.0% | 73.3% | ↑ 13.3% |
-| Medical | 73.3% | 80.0% | ↑ 6.7% |
-| Linux | 93.3% | 93.3% | → |
-| Writing | 60.0% | 53.3% | ↓ 6.7% |
+| **Python** | 76.9% | 61.5% ⭐ | ↓ 15.4% |
+| Html | 20.0% | 10.0% | ↓ 10.0% |
+| Trivia | 86.7% | 53.3% | ↓ 33.3% |
+| Math | 80.0% | 93.3% | ↑ 13.3% |
+| Reasoning | 75.0% | 50.0% | ↓ 25.0% |
+| Medical | 42.9% | 14.3% | ↓ 28.6% |
+| Linux | 23.1% | 23.1% | → |
+| Writing | 54.5% | 0.0% | ↓ 54.5% |
 
-**Average**: 50.0% → 54.2% (+4.2%)
+**Average**: 57.4% → 38.2% (-19.2%)
 
-**Python Retention**: 100.0% of original performance
+**Python Retention**: 80.0%
 
 ![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/EXAONE-4.0-1.2B-python-aggressive")
 tokenizer = AutoTokenizer.from_pretrained("CompactAI/EXAONE-4.0-1.2B-python-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 | [LGAI-EXAONE/EXAONE-4.0-1.2B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B) |
 | Specialization | Python |
 | Prune Mode | Aggressive |
-| Pruning Method | Activation-based weight pruning (Wanda) |
-| Weight Reduction | 7% weights pruned |
-
-## 🔗 Related Models
+| Weight Reduction | 30% weights pruned |
 
-This model is part of the **EXAONE-4.0-1.2B** 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 [LGAI-EXAONE/EXAONE-4.0-1.2B](https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B).
-
----
-*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:feca229ba9acdac8b8075ead8c7c7f04862c3ca4e1477663ac287377d35dc46c
+oid sha256:c72a92b33c4db88f0addee7b4f1e9834012f6f341f038b04a7c0504c7601923e
 size 2558820960

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 64512,
+    "max_length": 65386,
     "strategy": "LongestFirst",
     "stride": 0
   },