def collate_fn()

in fine_tune/sft_vlm.py [0:0]

• 12 lines of code
• 9 McCabe index (conditional complexity)

    def collate_fn(examples):
        # Get the texts and images, and apply the chat template
        texts = [processor.apply_chat_template(example["messages"], tokenize=False) for example in examples]
        images = [example["images"] for example in examples]
        if isinstance(model, LlavaForConditionalGeneration):
            # LLava1.5 does not support multiple images
            images = [image[0] for image in images]

        # Tokenize the texts and process the images
        batch = processor(text=texts, images=images, return_tensors="pt", padding=True)

        # The labels are the input_ids, and we mask the padding tokens in the loss computation
        labels = batch["input_ids"].clone()
        labels[labels == processor.tokenizer.pad_token_id] = -100  #
        # Ignore the image token index in the loss computation (model specific)
        image_token_id = processor.tokenizer.convert_tokens_to_ids(processor.image_token)
        labels[labels == image_token_id] = -100
        batch["labels"] = labels

        return batch