import json import os from functools import lru_cache from typing import List, Optional, Tuple import regex as re from transformers import AddedToken, PreTrainedTokenizer import logging logger = logging.getLogger(__name__) VOCAB_FILES_NAMES = { "vocab_file": "vocab.json", "merges_file": "merges.txt", } # Taken from # https://github.com/huggingface/transformers/blob/8aca43bdb3cb9a5020f6d57589d85679dc873b1c/src/transformers/models/gpt2/tokenization_gpt2.py#L62-L84 @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 CodeSageTokenizer(PreTrainedTokenizer): """A thin wrapper of the starcoder tokenizer. See HuggingFace for further documentation on general tokenizer methods. """ vocab_files_names = VOCAB_FILES_NAMES model_input_names = ["input_ids", "attention_mask"] def __init__( self, vocab_file, merges_file, errors="replace", unk_token="<|endoftext|>", bos_token="<|endoftext|>", eos_token="<|endoftext|>", pad_token=None, add_prefix_space=False, add_bos_token=False, add_eos_token=True, **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 self.add_bos_token = add_bos_token self.add_eos_token = add_eos_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+""") 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, add_eos_token=add_eos_token, **kwargs, ) @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: List[int], token_ids_1: Optional[List[int]] = None) -> List[int]: bos_token_id = [self.bos_token_id] if self.add_bos_token else [] eos_token_id = [self.eos_token_id] if self.add_eos_token else [] output = bos_token_id + token_ids_0 + eos_token_id if token_ids_1 is not None: output = output + bos_token_id + token_ids_1 + eos_token_id return output def get_special_tokens_mask( self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False ) -> List[int]: """ Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` or `encode_plus` methods. Args: token_ids_0 (`List[int]`): List of IDs. token_ids_1 (`List[int]`, *optional*): Optional second list of IDs for sequence pairs. already_has_special_tokens (`bool`, *optional*, defaults to `False`): Whether or not the token list is already formatted with special tokens for the model. Returns: `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. """ if already_has_special_tokens: return super().get_special_tokens_mask( token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True ) if not self.add_bos_token: return super().get_special_tokens_mask( token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=False ) if token_ids_1 is None: return [1] + ([0] * len(token_ids_0)) return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(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) @property def default_chat_template(self): """ A simple chat template that ignores role information and just concatenates messages with EOS tokens. """ return "{% for message in messages %}" "{{ message.content }}{{ eos_token }}" "{% endfor %}"