Update README.md

README.md

@@ -10,7 +10,6 @@ tags:
 - txtimage-to-txt
 - lora
 ---
-完整模型过几日上传。
 
 ### 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力，达到gpt4o、claude-3.5-sonnet的识别水平！
 1. 模型结构：</br>
@@ -47,36 +46,6 @@ llava-Qwen2-7B-Instruct-Chinese-CLIP = Qwen/Qwen2-7B-Instruct + multi_modal_proj
 <img src="./images/gpt4o-03.JPG" width="600" height="400">
 
 6. 代码</br>
-合并模型代码，合并模型之后将add_tokens.json,merge.txt,preprocessor_config.json,specital_token_map.json,tokenizer.json,vocab.json文件复制到"/保存的完整模型路径"。
-```python
-import torch
-from peft import PeftModel, LoraConfig
-from transformers import LlavaForConditionalGeneration
-model_name = "/替换为你的基础模型路径"
-LORA_R = 32
-LORA_ALPHA = 64
-LORA_DROPOUT = 0.05
-TARGET_MODULES = ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]
-lora_config = LoraConfig(
-    r=LORA_R,
-    lora_alpha=LORA_ALPHA,
-    target_modules=TARGET_MODULES,
-    lora_dropout=LORA_DROPOUT,
-    bias="none",
-    task_type="CAUSAL_LM",
-    modules_to_save=["multi_modal_projector"],
-) 
-model = LlavaForConditionalGeneration.from_pretrained(model_name)
-model = PeftModel.from_pretrained(model, "/替换为你的lora模型路径", config=lora_config, adapter_name='lora')
-
-model.cpu()
-model.eval()
-base_model = model.get_base_model()
-base_model.eval()
-model.merge_and_unload()
-base_model.save_pretrained("/保存的完整模型路径")
-```
-
 推理代码
 ```python
 from transformers import LlavaForConditionalGeneration, AutoProcessor