Qwen2.5 Lora微调代码的小问题

[YoungZSh]

在Qwen2.5 Lora微调代码中，process_func在对response进行分词时是否应该添加<|im_end|>\n：

def process_func(example):
    MAX_LENGTH = 384 
    input_ids, attention_mask, labels = [], [], []
    instruction = tokenizer(f"<|im_start|>system\n现在你要扮演皇帝身边的女人--甄嬛<|im_end|>\n<|im_start|>user\n{example['instruction'] + example['input']}<|im_end|>\n<|im_start|>assistant\n", add_special_tokens=False) 
    response = tokenizer(f"{example['output']}<|im_end|>\n", add_special_tokens=False) # <=代码修改
    input_ids = instruction["input_ids"] + response["input_ids"] + [tokenizer.pad_token_id]
    attention_mask = instruction["attention_mask"] + response["attention_mask"] + [1] 
    labels = [-100] * len(instruction["input_ids"]) + response["input_ids"] + [tokenizer.pad_token_id]  
    if len(input_ids) > MAX_LENGTH:
        input_ids = input_ids[:MAX_LENGTH]
        attention_mask = attention_mask[:MAX_LENGTH]
        labels = labels[:MAX_LENGTH]
    return {
        "input_ids": input_ids,
        "attention_mask": attention_mask,
        "labels": labels
    }

参考来源是Qwen的官方示例：

<|im_start|>system
You are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>
<|im_start|>user
hello<|im_end|>
<|im_start|>assistant
Hello! How can I assist you today? Let me know if you have any questions or need help with something. I'm here to help!<|im_end|>
<|im_start|>user
Explain large language models like I'm 5.<|im_end|>
<|im_start|>assistant
Sure, I'd be happy to explain large language models in a simple way!
Imagine that you have a friend who is really good at playing with words. This friend has read so many books and talked to so many people that they know how to use words in all sorts of different ways. They can tell stories, answer questions, and even make up new words if they need to.
Now imagine that this friend is actually a computer program, called a "large language model". It's been trained on lots and lots of text, like books, articles, and conversations, so it knows how to use words just like your word-loving friend does. When you ask the model a question or give it a task, it uses all the knowledge it's learned to come up with a response that makes sense.
Just like your friend might sometimes make mistakes or say things in a funny way, the large language model isn't perfect either. But it's still really impressive, because it can understand and generate human language in a way that was once thought impossible for machines!<|im_end|><|endoftext|>