Update README.md

README.md

@@ -197,21 +197,13 @@ print(processor.decode(outputs[0], skip_special_tokens=False))
 
 The model was abliterated using **PRISM** - a state-of-the-art abliteration methodology combining multiple principled techniques for effective refusal removal while preserving model capabilities.
 
-**Core Approach:**
 
-1. **Per-Layer Refusal Direction** - Each layer gets its own unique refusal direction (`r = harmful_mean - harmless_mean`) instead of a single global direction
-2. **Projected Direction Isolation** - Projects refusal direction orthogonal to harmless subspace to avoid "helpfulness confound"
-3. **Dynamic Layer-Wise Weight Kernel** - Bell curve distribution focusing on middle layers where refusal is encoded (weights range 0.45 to 2.24)
-4. **Winsorization** - Clips extreme values for numerical stability
-5. **KL Divergence Preservation** - Maintains 0.0000 KL divergence across all layers
-
-**Key Innovation:** Per-layer refusal directions preserve layer-specific behavior better than global averaging approaches.
 
 ## Hardware Requirements
 
 | Quantization | Min RAM/VRAM | Recommended | Hardware Examples |
 |-------------|--------------|-------------|-------------------|
-| IQ4_XS | 8 GB | 12+ GB | RTX 3060 12GB, RTX 4070, Apple M1/M2/M3/M4 |
+| IQ4_XS | T GB | 12+ GB | RTX 3060 12GB, RTX 4070, Apple M1/M2/M3/M4 |
 
 ### Tested Configurations
 
@@ -220,7 +212,7 @@ The model was abliterated using **PRISM** - a state-of-the-art abliteration meth
 | NVIDIA RTX GPU | 12+ GB | Works |
 | Apple Silicon | 16+ GB Unified | Works |
 
-**Note:** This is a relatively lightweight model that can run on consumer hardware with 12GB+ VRAM.
+**Note:** This is a relatively lightweight model that can run on consumer hardware with 12GB+ or less VRAM.
 
 ## Vision Capabilities