tokenization_moss.py

"""Tokenization classes for Moss"""

import json
import os
import numpy as np
import regex as re

from functools import lru_cache
from typing import TYPE_CHECKING, List, Optional, Tuple, Union

from transformers.utils import is_tf_available, is_torch_available, logging
from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer


if TYPE_CHECKING:
    if is_torch_available():
        import torch
    if is_tf_available():
        import tensorflow as tf


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {
    "vocab_file": "vocab.json",
    "merges_file": "merges.txt",
}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "fnlp/moss-moon-003-base": "https://huggingface.co/fnlp/moss-moon-003-base/resolve/main/vocab.json",
        "fnlp/moss-moon-003-sft": "https://huggingface.co/fnlp/moss-moon-003-sft/resolve/main/vocab.json",
        "fnlp/moss-moon-003-sft-plugin": "https://huggingface.co/fnlp/moss-moon-003-sft-plugin/resolve/main/vocab.json",
    },
    "merges_file": {
        "fnlp/moss-moon-003-base": "https://huggingface.co/fnlp/moss-moon-003-base/resolve/main/merge.txt",
        "fnlp/moss-moon-003-sft": "https://huggingface.co/fnlp/moss-moon-003-sft/resolve/main/merge.txt",
        "fnlp/moss-moon-003-sft-plugin": "https://huggingface.co/fnlp/moss-moon-003-sft-plugin/resolve/main/merge.txt",
    },
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "fnlp/moss-moon-003-base": 2048,
    "fnlp/moss-moon-003-sft": 2048,
    "fnlp/moss-moon-003-sft-plugin": 2048,
}


@lru_cache()
def bytes_to_unicode():
    """
    Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control
    characters the bpe code barfs on.

    The reversible bpe codes work on unicode strings. This means you need a large # of unicode characters in your vocab
    if you want to avoid UNKs. When you're at something like a 10B token dataset you end up needing around 5K for
    decent coverage. This is a significant percentage of your normal, say, 32K bpe vocab. To avoid that, we want lookup
    tables between utf-8 bytes and unicode strings.
    """
    bs = (
        list(range(ord("!"), ord("~") + 1)) + list(range(ord("¡"), ord("¬") + 1)) + list(range(ord("®"), ord("ÿ") + 1))
    )
    cs = bs[:]
    n = 0
    for b in range(2**8):
        if b not in bs:
            bs.append(b)
            cs.append(2**8 + n)
            n += 1
    cs = [chr(n) for n in cs]
    return dict(zip(bs, cs))


def get_pairs(word):
    """
    Return set of symbol pairs in a word.

    Word is represented as tuple of symbols (symbols being variable-length strings).
    """
    pairs = set()
    prev_char = word[0]
    for char in word[1:]:
        pairs.add((prev_char, char))
        prev_char = char
    return pairs


class MossTokenizer(PreTrainedTokenizer):
    """
    Construct a Moss tokenizer. Based on byte-level Byte-Pair-Encoding.

    This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
    be encoded differently whether it is at the beginning of the sentence (without space) or not:

    You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer or when you
    call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.

    <Tip>

    When used with `is_split_into_words=True`, this tokenizer will add a space before each word (even the first one).

    </Tip>

    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
    this superclass for more information regarding those methods.

    Args:
        vocab_file (`str`):
            Path to the vocabulary file.
        merges_file (`str`):
            Path to the merges file.
        errors (`str`, *optional*, defaults to `"replace"`):
            Paradigm to follow when decoding bytes to UTF-8. See
            [bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information.
        unk_token (`str`, *optional*, defaults to `<|endoftext|>`):
            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
            token instead.
        bos_token (`str`, *optional*, defaults to `<|endoftext|>`):
            The beginning of sequence token.
        eos_token (`str`, *optional*, defaults to `<|endoftext|>`):
            The end of sequence token.
        add_prefix_space (`bool`, *optional*, defaults to `False`):
            Whether or not to add an initial space to the input. This allows to treat the leading word just as any
            other word. (Moss tokenizer detect beginning of words by the preceding space).
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        vocab_file,
        merges_file,
        errors="replace",
        unk_token="<|endoftext|>",
        bos_token="<|endoftext|>",
        eos_token="<eom>",
        pad_token=None,
        add_prefix_space=False,
        add_bos_token=False,
        **kwargs,
    ):
        bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
        eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
        unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
        super().__init__(
            errors=errors,
            unk_token=unk_token,
            bos_token=bos_token,
            eos_token=eos_token,
            pad_token=pad_token,
            add_prefix_space=add_prefix_space,
            add_bos_token=add_bos_token,
            **kwargs,
        )
        self.add_bos_token = add_bos_token

        with open(vocab_file, encoding="utf-8") as vocab_handle:
            self.encoder = json.load(vocab_handle)
        self.decoder = {v: k for k, v in self.encoder.items()}
        self.errors = errors  # how to handle errors in decoding
        self.byte_encoder = bytes_to_unicode()
        self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
        with open(merges_file, encoding="utf-8") as merges_handle:
            bpe_merges = merges_handle.read().split("\n")[1:-1]
        bpe_merges = [tuple(merge.split()) for merge in bpe_merges]
        self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
        self.cache = {}
        self.add_prefix_space = add_prefix_space

        # Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
        self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""")

    @property
    def vocab_size(self):
        return len(self.encoder)

    def get_vocab(self):
        return dict(self.encoder, **self.added_tokens_encoder)

    def bpe(self, token):
        if token in self.cache:
            return self.cache[token]
        word = tuple(token)
        pairs = get_pairs(word)

        if not pairs:
            return token

        while True:
            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
            if bigram not in self.bpe_ranks:
                break
            first, second = bigram
            new_word = []
            i = 0
            while i < len(word):
                try:
                    j = word.index(first, i)
                except ValueError:
                    new_word.extend(word[i:])
                    break
                else:
                    new_word.extend(word[i:j])
                    i = j

                if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
                    new_word.append(first + second)
                    i += 2
                else:
                    new_word.append(word[i])
                    i += 1
            new_word = tuple(new_word)
            word = new_word
            if len(word) == 1:
                break
            else:
                pairs = get_pairs(word)
        word = " ".join(word)
        self.cache[token] = word
        return word

    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
        if self.add_bos_token:
            bos_token_ids = [self.bos_token_id]
        else:
            bos_token_ids = []

        output = bos_token_ids + token_ids_0

        if token_ids_1 is None:
            return output

        return output + bos_token_ids + token_ids_1

    def _tokenize(self, text):
        """Tokenize a string."""
        bpe_tokens = []
        for token in re.findall(self.pat, text):
            token = "".join(
                self.byte_encoder[b] for b in token.encode("utf-8")
            )  # Maps all our bytes to unicode strings, avoiding control tokens of the BPE (spaces in our case)
            bpe_tokens.extend(bpe_token for bpe_token in self.bpe(token).split(" "))
        return bpe_tokens

    def _convert_token_to_id(self, token):
        """Converts a token (str) in an id using the vocab."""
        return self.encoder.get(token, self.encoder.get(self.unk_token))

    def _convert_id_to_token(self, index):
        """Converts an index (integer) in a token (str) using the vocab."""
        return self.decoder.get(index)

    def convert_tokens_to_string(self, tokens):
        """Converts a sequence of tokens (string) in a single string."""
        text = "".join(tokens)
        text = bytearray([self.byte_decoder[c] for c in text]).decode("utf-8", errors=self.errors)
        return text

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        if not os.path.isdir(save_directory):
            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
            return
        vocab_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
        )
        merge_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
        )

        with open(vocab_file, "w", encoding="utf-8") as f:
            f.write(json.dumps(self.encoder, indent=2, sort_keys=True, ensure_ascii=False) + "\n")

        index = 0
        with open(merge_file, "w", encoding="utf-8") as writer:
            writer.write("#version: 0.2\n")
            for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
                if index != token_index:
                    logger.warning(
                        f"Saving vocabulary to {merge_file}: BPE merge indices are not consecutive."
                        " Please check that the tokenizer is not corrupted!"
                    )
                    index = token_index
                writer.write(" ".join(bpe_tokens) + "\n")
                index += 1

        return vocab_file, merge_file

    def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs):
        add_prefix_space = kwargs.pop("add_prefix_space", self.add_prefix_space)
        if is_split_into_words or add_prefix_space:
            text = " " + text
        return (text, kwargs)

    def decode(
        self,
        token_ids: Union[int, List[int], "np.ndarray", "torch.Tensor", "tf.Tensor"],
        skip_special_tokens: bool = False,
        clean_up_tokenization_spaces: bool = None,
        truncate_before_pattern: Optional[List[str]] = None,
        **kwargs,
    ) -> str:
        """
        Converts a sequence of ids in a string, using the tokenizer and vocabulary with options to remove special
        tokens and clean up tokenization spaces.

        Similar to doing `self.convert_tokens_to_string(self.convert_ids_to_tokens(token_ids))`.

        Args:
            token_ids (`Union[int, List[int], np.ndarray, torch.Tensor, tf.Tensor]`):
                List of tokenized input ids. Can be obtained using the `__call__` method.
            skip_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not to remove special tokens in the decoding.
            clean_up_tokenization_spaces (`bool`, *optional*):
                Whether or not to clean up the tokenization spaces. If `None`, will default to
                `self.clean_up_tokenization_spaces` (available in the `tokenizer_config`).
            truncate_before_pattern (`List[str]`, *optional*, defaults to `None`):
                A list of regular expression strings that will be used to truncate the returned string. This can be
                used to remove extra pieces of code (e.g. truncate if observing a comment symbol "#" at the beginning
                of a new line). An example pattern could be `["^#", re.escape("<|endoftext|>"), "^'''", "\n\n\n"]`.
            kwargs (additional keyword arguments, *optional*):
                Will be passed to the underlying model specific decode method.

        Returns:
            `str`: The decoded sentence.
        """
        decoded_text = super()._decode(
            token_ids=token_ids,
            skip_special_tokens=skip_special_tokens,
            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
            **kwargs,
        )

        if truncate_before_pattern is not None and len(truncate_before_pattern) > 0:
            decoded_text = self.truncate(decoded_text, truncate_before_pattern)

        return decoded_text

    def truncate(self, completion, truncate_before_pattern):
        def find_re(string, pattern, start_pos):
            m = pattern.search(string, start_pos)
            return m.start() if m else -1

        terminals = [re.compile(pattern, re.MULTILINE) for pattern in truncate_before_pattern]

        prints = list(re.finditer("^print", completion, re.MULTILINE))

        if len(prints) > 1:
            completion = completion[: prints[1].start()]

        defs = list(re.finditer("^def", completion, re.MULTILINE))

        if len(defs) > 1:
            completion = completion[: defs[1].start()]

        start_pos = 0

        terminals_pos = [
            pos for pos in [find_re(completion, terminal, start_pos) for terminal in terminals] if pos != -1
        ]

        if len(terminals_pos) > 0:
            return completion[: min(terminals_pos)]
        else:
            return completion