Update README.md

README.md

@@ -134,9 +134,9 @@ This SFT approach enables Alpie-Core to deliver reliable, aligned, and context-a
 
 - **Hardware**: 8× NVIDIA H100-80GB GPUs
 - **Fine-tuning Method**: LoRA/QLoRA with the following configuration:
-  - LoRA Alpha: 8
+  - LoRA Alpha: 16
   - LoRA Dropout: 0.05
-  - LoRA Rank: 8
+  - LoRA Rank: 16
 - **Quantization**: 4-bit NF4 + Double Quantization + FP16 compute
 - **Dataset Domains**: Mathematics, coding, reasoning, science, general knowledge, competitive exams, Indian context + law, multilingual (Hindi and Hinglish)
 - **Synthetic Data Advantage**: +15-20% performance boost in STEM & coding domains