Function preprocess_v1

llava/train/train.py:414–497

(
    sources,
    tokenizer: transformers.PreTrainedTokenizer,
    has_image: bool = False
)

def preprocess_v1(
    sources,
    tokenizer: transformers.PreTrainedTokenizer,
    has_image: bool = False
) -> Dict:
    conv = conversation_lib.default_conversation.copy()
    roles = {"human": conv.roles[0], "gpt": conv.roles[1]}

    # Apply prompt templates
    conversations = []
    for i, source in enumerate(sources):
        if roles[source[0]["from"]] != conv.roles[0]:
            # Skip the first one if it is not from human
            source = source[1:]

        conv.messages = []
        for j, sentence in enumerate(source):
            role = roles[sentence["from"]]
            assert role == conv.roles[j % 2], f"{i}"
            conv.append_message(role, sentence["value"])
        conversations.append(conv.get_prompt())

    # Tokenize conversations

    if has_image:
        input_ids = torch.stack([tokenizer_image_token(prompt, tokenizer, return_tensors='pt') for prompt in conversations], dim=0)
    else:
        input_ids = tokenizer(
            conversations,
            return_tensors="pt",
            padding="longest",
            max_length=tokenizer.model_max_length,
            truncation=True,
        ).input_ids

    targets = input_ids.clone()

    assert conv.sep_style == conversation_lib.SeparatorStyle.TWO

    # Mask targets
    sep = conv.sep + conv.roles[1] + ": "
    for conversation, target in zip(conversations, targets):
        total_len = int(target.ne(tokenizer.pad_token_id).sum())

        rounds = conversation.split(conv.sep2)
        cur_len = 1
        target[:cur_len] = IGNORE_INDEX
        for i, rou in enumerate(rounds):
            if rou == "":
                break

            parts = rou.split(sep)
            if len(parts) != 2:
                break
            parts[0] += sep

            if has_image:
                round_len = len(tokenizer_image_token(rou, tokenizer))