finetune llama2 error1

transformers版本更新，没有top_k_top_p_filtering()函数了，可以安装合适版本的transformers(<=4.38.2)
我这里选择偷懒，直接将相关函数添加到/***/***/lib/python3.10/site-packages/trl/core.py中

class LogitsWarper:
    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
        raise NotImplementedError(
            f"{self.__class__} is an abstract class. Only classes inheriting this class can be called."
        )

class TopPLogitsWarper(LogitsWarper):
    def __init__(self, top_p: float, filter_value: float = -float("Inf"), min_tokens_to_keep: int = 1):
        top_p = float(top_p)
        if top_p < 0 or top_p > 1.0:
            raise ValueError(f"`top_p` has to be a float > 0 and < 1, but is {top_p}")
        if not isinstance(min_tokens_to_keep, int) or (min_tokens_to_keep < 1):
            raise ValueError(f"`min_tokens_to_keep` has to be a positive integer, but is {min_tokens_to_keep}")

        self.top_p = top_p
        self.filter_value = filter_value
        self.min_tokens_to_keep = min_tokens_to_keep

    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
        sorted_logits, sorted_indices = torch.sort(scores, descending=False)
        cumulative_probs = sorted_logits.softmax(dim=-1).cumsum(dim=-1)

        # Remove tokens with cumulative top_p above the threshold (token with 0 are kept)
        sorted_indices_to_remove = cumulative_probs <= (1 - self.top_p)
        # Keep at least min_tokens_to_keep
        sorted_indices_to_remove[..., -self.min_tokens_to_keep :] = 0

        # scatter sorted tensors to original indexing
        indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
        scores = scores.masked_fill(indices_to_remove, self.filter_value)
        return scores

class TopKLogitsWarper(LogitsWarper):
    def __init__(self, top_k: int, filter_value: float = -float("Inf"), min_tokens_to_keep: int = 1):
        if not isinstance(top_k, int) or top_k <= 0:
            raise ValueError(f"`top_k` has to be a strictly positive integer, but is {top_k}")

        self.top_k = max(top_k, min_tokens_to_keep)
        self.filter_value = filter_value

    def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
        top_k = min(self.top_k, scores.size(-1))  # Safety check
        # Remove all tokens with a probability less than the last token of the top-k
        indices_to_remove = scores < torch.topk(scores, top_k)[0][..., -1, None]
        scores = scores.masked_fill(indices_to_remove, self.filter_value)
        return scores

def top_k_top_p_filtering(
    logits: torch.FloatTensor,
    top_k: int = 0,
    top_p: float = 1.0,
    filter_value: float = -float("Inf"),
    min_tokens_to_keep: int = 1,
) -> torch.FloatTensor:
    if top_k > 0:
        logits = TopKLogitsWarper(top_k=top_k, filter_value=filter_value, min_tokens_to_keep=min_tokens_to_keep)(
            None, logits
        )

    if 0 <= top_p <= 1.0:
        logits = TopPLogitsWarper(top_p=top_p, filter_value=filter_value, min_tokens_to_keep=min_tokens_to_keep)(
            None, logits
        )

    return logits