Function _prepare_messages

rft/trainer/utils/process.py:5–46

(
    prompts,
    processing_class,
    max_prompt_length
)

from PIL import Image

def _prepare_messages(
    prompts,
    processing_class,
    max_prompt_length
):
    prompts_lists = []
    input_images_lists = []

    for msgs in prompts:
        copy_msgs = copy.deepcopy(msgs)
        
        images = []
        for i, msg in enumerate(copy_msgs):
            role, content = msg["role"], msg["content"]
            
            if isinstance(content,str):
                content = [content]
            cur_msgs = []
            for c in content:
                if isinstance(c, Image.Image):
                    images.append(c)
                    cur_msgs.append("(<image>./</image>)")
                elif isinstance(c, str):
                    cur_msgs.append(c)
            msg['content'] = "\n".join(cur_msgs)
        
        prompts_lists.append(
            processing_class.tokenizer.apply_chat_template(copy_msgs, tokenize=False, add_generation_prompt=True)
        )
        input_images_lists.append(images)
    
    ret = processing_class(
        prompts_lists,
        input_images_lists,
        return_tensors="pt",
        max_length=max_prompt_length
    )
    
    
    return {
        **ret
    }

def _create_inputs(
    processing_class,