Update README.md

README.md

@@ -11,9 +11,9 @@ tags:
 # 🔥 Quantized Model: Mistral-Small-24B-Instruct-2501_gptq_g32_4bit 🔥
 
 This is a 4-bit quantized version of [mistralai/Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501) model, quantized by [ConfidentialMind.com](https://www.confidentialmind.com) 🤖✨  
-It leverages the open-source GPTQModel quantization to achieve 4-bit precision with a group size of 128 resulting in a 
+It leverages the open-source GPTQModel quantization to achieve 4-bit precision with a group size of 32 resulting in a 
 smaller, 
-faster model with minimal performance degradation.
+faster model with minimal performance degradation. The G128 variant used MSE loss in order to avoid performance degredation.
 
 Ran on a single NVIDIA A100 GPU with 80GB of VRAM.