Update README.md

README.md

@@ -20,7 +20,7 @@ llava-Qwen2-7B-Instruct-CLIP-ZH = Qwen/Qwen2-7B-Instruct + multi_modal_projector
 - mmp层全量训练</br>
 
 3. 微调参数</br>
-lora_r=32, lora_alpha=64,num_train_epochs=5,per_device_train_batch_size=1,gradient_accumulation_steps=8,high_lr=1e-3,low_lr=2e-5,model_max_length=2048
+lora_r=32,lora_alpha=64,num_train_epochs=5,per_device_train_batch_size=1,gradient_accumulation_steps=8,high_lr=1e-3,low_lr=2e-5,model_max_length=2048
 
 4. 数据集</br>
 使用gemini-1.5-pro, gemini-1.5-flash, yi-vision, gpt4o,claude-3.5-sonnet模型描述emo-visual-data和ChineseBQB数据集。</br>