| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| """Tokenization classes for Molformer.""" |
| from typing import List, Optional, Tuple |
|
|
| from transformers.tokenization_utils_fast import PreTrainedTokenizerFast |
| from transformers.utils import logging |
| from .tokenization_molformer import MolformerTokenizer |
|
|
|
|
| logger = logging.get_logger(__name__) |
|
|
| VOCAB_FILES_NAMES = {"vocab_file": "vocab.json", "tokenizer_file": "tokenizer.json"} |
|
|
| PRETRAINED_VOCAB_FILES_MAP = { |
| "vocab_file": { |
| "ibm/MoLFormer-XL-both-10pct": "https://huggingface.co/ibm/MoLFormer-XL-both-10pct/resolve/main/vocab.json", |
| } |
| } |
|
|
| PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { |
| "ibm/MoLFormer-XL-both-10pct": 202, |
| } |
|
|
|
|
| class MolformerTokenizerFast(PreTrainedTokenizerFast): |
| r""" |
| Construct a "fast" Molformer tokenizer. |
| |
| This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should |
| refer to this superclass for more information regarding those methods. |
| |
| Args: |
| vocab_file (`str`, *optional*): |
| File containing the vocabulary. |
| tokenizer_file (`str`, *optional*): |
| The path to a tokenizer file to use instead of the vocab file. |
| unk_token (`str`, *optional*, defaults to `"<unk>"`): |
| 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. |
| sep_token (`str`, *optional*, defaults to `"<eos>"`): |
| The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for |
| sequence classification or for a text and a question for question answering. It is also used as the last |
| token of a sequence built with special tokens. |
| pad_token (`str`, *optional*, defaults to `"<pad>"`): |
| The token used for padding, for example when batching sequences of different lengths. |
| cls_token (`str`, *optional*, defaults to `"<bos>"`): |
| The classifier token which is used when doing sequence classification (classification of the whole sequence |
| instead of per-token classification). It is the first token of the sequence when built with special tokens. |
| mask_token (`str`, *optional*, defaults to `"<mask>"`): |
| The token used for masking values. This is the token used when training this model with masked language |
| modeling. This is the token which the model will try to predict. |
| """ |
|
|
| 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"] |
| slow_tokenizer_class = MolformerTokenizer |
|
|
| def __init__( |
| self, |
| vocab_file=None, |
| tokenizer_file=None, |
| unk_token="<unk>", |
| sep_token="<eos>", |
| pad_token="<pad>", |
| cls_token="<bos>", |
| mask_token="<mask>", |
| **kwargs, |
| ): |
| super().__init__( |
| vocab_file, |
| tokenizer_file=tokenizer_file, |
| unk_token=unk_token, |
| sep_token=sep_token, |
| pad_token=pad_token, |
| cls_token=cls_token, |
| mask_token=mask_token, |
| **kwargs, |
| ) |
|
|
| |
| def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None): |
| """ |
| Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and |
| adding special tokens. A BERT sequence has the following format: |
| |
| - single sequence: `[CLS] X [SEP]` |
| - pair of sequences: `[CLS] A [SEP] B [SEP]` |
| |
| Args: |
| token_ids_0 (`List[int]`): |
| List of IDs to which the special tokens will be added. |
| token_ids_1 (`List[int]`, *optional*): |
| Optional second list of IDs for sequence pairs. |
| |
| Returns: |
| `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens. |
| """ |
| output = [self.cls_token_id] + token_ids_0 + [self.sep_token_id] |
|
|
| if token_ids_1 is not None: |
| output += token_ids_1 + [self.sep_token_id] |
|
|
| return output |
|
|
| |
| 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. A BERT sequence |
| pair mask has the following format: |
| |
| ``` |
| 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1 |
| | first sequence | second sequence | |
| ``` |
| |
| If `token_ids_1` is `None`, this method only returns the first portion of the mask (0s). |
| |
| 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 [token type IDs](../glossary#token-type-ids) according to the given sequence(s). |
| """ |
| sep = [self.sep_token_id] |
| cls = [self.cls_token_id] |
| if token_ids_1 is None: |
| return len(cls + token_ids_0 + sep) * [0] |
| return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1] |
|
|
| |
| def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]: |
| files = self._tokenizer.model.save(save_directory, name=filename_prefix) |
| return tuple(files) |
|
|
