使用PEFT库将原始模型与LoRA权重合并

步骤如下：

• 基础模型加载：需保持与LoRA训练时相同的模型配置
• merge_and_unload()：该方法会执行权重合并并移除LoRA层
• 保存格式：合并后的模型保存为标准HuggingFace格式，可直接用于推理
• 代码如下：

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizerdef merge_and_save_model(base_model_path, lora_path, output_path):# 1. 加载基础模型和tokenizerprint(f"Loading base model from {base_model_path}")base_model = AutoModelForCausalLM.from_pretrained(base_model_path,torch_dtype=torch.bfloat16,device_map="auto",trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained(base_model_path,trust_remote_code=True)# 2. 加载LoRA适配器print(f"Loading LoRA adapter from {lora_path}")lora_model = PeftModel.from_pretrained(base_model,lora_path,torch_dtype=torch.float16)# 3. 合并权重并卸载适配器print("Merging LoRA weights with base model")merged_model = lora_model.merge_and_unload()# 4. 保存合并后的模型print(f"Saving merged model to {output_path}")merged_model.save_pretrained(output_path)tokenizer.save_pretrained(output_path)print("Merge completed successfully!")# 使用示例
if __name__ == "__main__":merge_and_save_model(base_model_path= 基础模型路径lora_path= lora训练后的权重output_path= 合并后模型的输出路径)