df

tokenizeConfig.py

@@ -1,9 +1,9 @@
-"""Tokenization classes for IntermLM."""
 import os
 from shutil import copyfile
 from typing import Any, Dict, List, Optional, Tuple
 
-import sentencepiece as spm
+import tokenizers
+from tokenizers import models, pre_tokenizers, decoders, trainers
 
 from transformers.tokenization_utils import PreTrainedTokenizer
 from transformers.utils import logging
@@ -36,14 +36,11 @@ class OBITokenizer(PreTrainedTokenizer):
         bos_token="<s>",
         eos_token="</s>",
         pad_token="</s>",
-        sp_model_kwargs: Optional[Dict[str, Any]] = None,
         add_bos_token=True,
         add_eos_token=False,
-        decode_with_prefix_space=False,
         clean_up_tokenization_spaces=False,
         **kwargs,
     ):
-        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
         super().__init__(
             bos_token=bos_token,
             eos_token=eos_token,
@@ -55,12 +52,14 @@ class OBITokenizer(PreTrainedTokenizer):
         self.vocab_file = vocab_file
         self.add_bos_token = add_bos_token
         self.add_eos_token = add_eos_token
-        self.decode_with_prefix_space = decode_with_prefix_space
-        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
-        self.sp_model.Load(vocab_file)
-        self._no_prefix_space_tokens = None
+        self.tokenizer = tokenizers.Tokenizer(models.BPE())
+        self.tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel()
+        self.tokenizer.decoder = decoders.ByteLevel()
+        self.tokenizer.post_processor = tokenizers.processors.ByteLevel()
+        self.tokenizer.enable_truncation(max_length=512)  # Adjust max_length as needed
+        self.tokenizer.enable_padding(max_length=512, pad_token="[PAD]")  # Adjust max_length and pad_token as needed
 
-        """ Initialisation"""
+        self._no_prefix_space_tokens = None
 
     @property
     def no_prefix_space_tokens(self):
@@ -72,15 +71,15 @@ class OBITokenizer(PreTrainedTokenizer):
     @property
     def vocab_size(self):
         """Returns vocab size"""
-        return self.sp_model.get_piece_size()
+        return len(self.tokenizer.get_vocab())
 
     @property
     def bos_token_id(self) -> Optional[int]:
-        return self.sp_model.bos_id()
+        return self.tokenizer.token_to_id("<s>")
 
     @property
     def eos_token_id(self) -> Optional[int]:
-        return self.sp_model.eos_id()
+        return self.tokenizer.token_to_id("</s>")
 
     def get_vocab(self):
         """Returns vocab as a dict"""
@@ -90,43 +89,20 @@ class OBITokenizer(PreTrainedTokenizer):
 
     def _tokenize(self, text):
         """Returns a tokenized string."""
-        return self.sp_model.encode(text, out_type=str)
+        encoding = self.tokenizer.encode(text)
+        return encoding.tokens
 
     def _convert_token_to_id(self, token):
         """Converts a token (str) in an id using the vocab."""
-        return self.sp_model.piece_to_id(token)
+        return self.tokenizer.token_to_id(token)
 
     def _convert_id_to_token(self, index):
         """Converts an index (integer) in a token (str) using the vocab."""
-        token = self.sp_model.IdToPiece(index)
-        return token
-
-    def _maybe_add_prefix_space(self, tokens, decoded):
-        if tokens and tokens[0] not in self.no_prefix_space_tokens:
-            return " " + decoded
-        else:
-            return decoded
+        return self.tokenizer.id_to_token(index)
 
     def convert_tokens_to_string(self, tokens):
-        """Converts a sequence of tokens (string) in a single string."""
-        current_sub_tokens = []
-        out_string = ""
-        prev_is_special = False
-        for token in tokens:
-            # make sure that special tokens are not decoded using sentencepiece model
-            if token in self.all_special_tokens:
-                if not prev_is_special:
-                    out_string += " "
-                out_string += self.sp_model.decode(current_sub_tokens) + token
-                prev_is_special = True
-                current_sub_tokens = []
-            else:
-                current_sub_tokens.append(token)
-                prev_is_special = False
-        out_string += self.sp_model.decode(current_sub_tokens)
-        out_string = self.clean_up_tokenization(out_string)
-        out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
-        return out_string[1:]
+        """Converts a sequence of tokens (string) into a single string."""
+        return self.tokenizer.decode(tokens).strip()
 
     def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
         """
@@ -144,72 +120,7 @@ class OBITokenizer(PreTrainedTokenizer):
             save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
         )
 
-        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
-            copyfile(self.vocab_file, out_vocab_file)
-        elif not os.path.isfile(self.vocab_file):
-            with open(out_vocab_file, "wb") as fi:
-                content_spiece_model = self.sp_model.serialized_model_proto()
-                fi.write(content_spiece_model)
+        # Save the BPE vocab
+        self.tokenizer.get_vocab().to_file(out_vocab_file)
 
         return (out_vocab_file,)
-
-    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 not None:
-            output = output + token_ids_1
-
-        if self.add_eos_token:
-            output = output + [self.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]:
-        """
-        Retrieve 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` method.
-        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 token_ids_1 is None:
-            return [1] + ([0] * len(token_ids_0)) + [1]
-        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
-
-    def create_token_type_ids_from_sequences(
-        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
-    ) -> List[int]:
-        """
-        Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
-        use of token type ids, therefore a list of zeros is returned.
-        Args:
-            token_ids_0 (`List[int]`):
-                List of IDs.
-            token_ids_1 (`List[int]`, *optional*):
-                Optional second list of IDs for sequence pairs.
-        Returns:
-            `List[int]`: List of zeros.
-        """
-        eos = [self.eos_token_id]
-
-        if token_ids_1 is None:
-            return len(token_ids_0 + eos) * [0]
-        return len(token_ids_0 + eos + token_ids_1 + eos) * [0]