Update pruned model - 8 files

README.md

@@ -11,24 +11,30 @@ pipeline_tag: text-generation
 
 # LFM2.5-1.2B-Base-python-safe
 
-> 🎯 **PYTHON-optimized** | 📦 **Safe** pruning | ⚡ **1% weights pruned**
+> **PYTHON-optimized** | **Safe** pruning | **30% weights pruned**
 
 This model is a **conservatively pruned** version of [LiquidAI/LFM2.5-1.2B-Base](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base).
 
+
+
+> **Note:** Minimal quality drop detected. The Wanda pruning algorithm effectively identifies and removes less important weights while preserving model capability.
+
+
+
 ## Performance Comparison
 
 | Category | Original | Pruned | Change |
 |----------|----------|--------|--------|
 | **Python** | 0.0% | 0.0% ⭐ | → |
-| Html | 16.7% | 16.7% | → |
-| Trivia | 91.7% | 91.7% | → |
-| Math | 75.0% | 75.0% | → |
-| Reasoning | 41.7% | 41.7% | → |
-| Medical | 66.7% | 66.7% | → |
-| Linux | 16.7% | 16.7% | → |
-| Writing | 33.3% | 33.3% | → |
+| Html | 0.0% | 0.0% | → |
+| Trivia | 15.0% | 15.0% | → |
+| Math | 15.0% | 15.0% | → |
+| Reasoning | 0.0% | 0.0% | → |
+| Medical | 20.0% | 20.0% | → |
+| Linux | 30.0% | 25.0% | ↓ 5.0% |
+| Writing | 5.0% | 5.0% | → |
 
-**Average**: 42.7% → 42.7% (+0.0%)
+**Average**: 10.6% -> 10.0% (-0.6%)
 
 
 
@@ -54,7 +60,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 | Base Model | [LiquidAI/LFM2.5-1.2B-Base](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base) |
 | Specialization | Python |
 | Prune Mode | Safe |
-| Weight Reduction | 1% weights pruned |
+| Weight Reduction | 30% weights pruned |
 
 ## License
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:867ff7c97d762500eccc24d3e257c136cc131b406f8ec9d4b134d9f502cc755a
+oid sha256:878bc57aaab79e1f145b2c1fcbf8ebea9547d45d344ee3a5d6e5fafda64d6150
 size 2340697784

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 127850,
+    "max_length": 126976,
     "strategy": "LongestFirst",
     "stride": 0
   },