Update README.md

README.md

@@ -21,9 +21,6 @@ A LoRA-adapted vision-language model based on Llama-3.2-11B-Vision-Instruct that
 ## Model Architecture
 
 - Base: Llama-3.2-11B-Vision-Instruct
-- Adaptation: LoRA (r=8, alpha=16)
-- Target: q_proj, v_proj attention layers
-- Training: 3 epochs, batch size 4, gradient accumulation 8, lr 2e-4
 
 ## Inference