Update README.md

README.md

@@ -41,7 +41,7 @@ We fine-tune OpenHathi base model on the aforementioned IndicInstruct dataset wi
 - LoRA Rank: 16
 - LoRA alpha: 32
 - LoRA Dropout: 0.05
-- LoRA Target Modules: ["q_proj", "v_proj", "down_proj", "gate_proj", "up_proj", "k_proj"]
+- LoRA Target Modules: ["q_proj", "v_proj", "k_proj", "o_proj", "down_proj", "gate_proj", "up_proj"]
 - Epochs: 4
 - Learning rate: 5e-4
 - Batch Size: 128