Update README.md

README.md

@@ -155,10 +155,10 @@ The model was trained on **~157,000 examples** from multiple high-quality Kubern
 - **Base Model**: unsloth/gemma-3-12b-it-qat-bnb-4bit
 - **Method**: LoRA (Low-Rank Adaptation)
 - **Framework**: Unsloth
-- **LoRA Rank**: 16
+- **LoRA Rank**: 8
 - **Target Modules**: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
 - **Training Checkpoint**: checkpoint-8175
-- **Max Sequence Length**: 2048 tokens
+- **Max Sequence Length**: 1024 tokens
 - **Training Time**: 28 hours
 - **Hardware**: NVIDIA GeForce RTX 5070 12GB