[Dependencies|tokenizers] Make both SentencePiece and Tokenizers optional dependencies (#7659)
* splitting fast and slow tokenizers [WIP] * [WIP] splitting sentencepiece and tokenizers dependencies * update dummy objects * add name_or_path to models and tokenizers * prefix added to file names * prefix * styling + quality * spliting all the tokenizer files - sorting sentencepiece based ones * update tokenizer version up to 0.9.0 * remove hard dependency on sentencepiece 🎉 * and removed hard dependency on tokenizers 🎉 * update conversion script * update missing models * fixing tests * move test_tokenization_fast to main tokenization tests - fix bugs * bump up tokenizers * fix bert_generation * update ad fix several tokenizers * keep sentencepiece in deps for now * fix funnel and deberta tests * fix fsmt * fix marian tests * fix layoutlm * fix squeezebert and gpt2 * fix T5 tokenization * fix xlnet tests * style * fix mbart * bump up tokenizers to 0.9.2 * fix model tests * fix tf models * fix seq2seq examples * fix tests without sentencepiece * fix slow => fast conversion without sentencepiece * update auto and bert generation tests * fix mbart tests * fix auto and common test without tokenizers * fix tests without tokenizers * clean up tests lighten up when tokenizers + sentencepiece are both off * style quality and tests fixing * add sentencepiece to doc/examples reqs * leave sentencepiece on for now * style quality split hebert and fix pegasus * WIP Herbert fast * add sample_text_no_unicode and fix hebert tokenization * skip FSMT example test for now * fix style * fix fsmt in example tests * update following Lysandre and Sylvain's comments * Update src/transformers/testing_utils.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/testing_utils.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/tokenization_utils_base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/tokenization_utils_base.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
This commit is contained in:
Thomas Wolf
@@ -4,9 +4,7 @@ from typing import Any, Callable, Dict, List, NewType, Optional, Tuple, Union
|
||||
import torch
|
||||
from torch.nn.utils.rnn import pad_sequence
|
||||
|
||||
from ..tokenization_utils import PreTrainedTokenizer
|
||||
from ..tokenization_utils_base import BatchEncoding, PaddingStrategy
|
||||
from ..tokenization_utils_fast import PreTrainedTokenizerFast
|
||||
from ..tokenization_utils_base import BatchEncoding, PaddingStrategy, PreTrainedTokenizerBase
|
||||
|
||||
|
||||
InputDataClass = NewType("InputDataClass", Any)
|
||||
@@ -94,7 +92,7 @@ class DataCollatorWithPadding:
|
||||
>= 7.5 (Volta).
|
||||
"""
|
||||
|
||||
tokenizer: Union[PreTrainedTokenizer, PreTrainedTokenizerFast]
|
||||
tokenizer: PreTrainedTokenizerBase
|
||||
padding: Union[bool, str, PaddingStrategy] = True
|
||||
max_length: Optional[int] = None
|
||||
pad_to_multiple_of: Optional[int] = None
|
||||
@@ -124,7 +122,7 @@ class DataCollatorForLanguageModeling:
|
||||
- preprocesses batches for masked language modeling
|
||||
"""
|
||||
|
||||
tokenizer: PreTrainedTokenizer
|
||||
tokenizer: PreTrainedTokenizerBase
|
||||
mlm: bool = True
|
||||
mlm_probability: float = 0.15
|
||||
|
||||
@@ -274,7 +272,7 @@ class DataCollatorForPermutationLanguageModeling:
|
||||
- preprocesses batches for permutation language modeling with procedures specific to XLNet
|
||||
"""
|
||||
|
||||
tokenizer: PreTrainedTokenizer
|
||||
tokenizer: PreTrainedTokenizerBase
|
||||
plm_probability: float = 1 / 6
|
||||
max_span_length: int = 5 # maximum length of a span of masked tokens
|
||||
|
||||
@@ -406,7 +404,7 @@ class DataCollatorForNextSentencePrediction:
|
||||
- preprocesses batches for masked language modeling
|
||||
"""
|
||||
|
||||
tokenizer: PreTrainedTokenizer
|
||||
tokenizer: PreTrainedTokenizerBase
|
||||
mlm: bool = True
|
||||
block_size: int = 512
|
||||
short_seq_probability: float = 0.1
|
||||
|
||||
@@ -9,10 +9,7 @@ from torch.utils.data.dataset import Dataset
|
||||
|
||||
from filelock import FileLock
|
||||
|
||||
from ...tokenization_bart import BartTokenizer, BartTokenizerFast
|
||||
from ...tokenization_roberta import RobertaTokenizer, RobertaTokenizerFast
|
||||
from ...tokenization_utils import PreTrainedTokenizer
|
||||
from ...tokenization_xlm_roberta import XLMRobertaTokenizer
|
||||
from ...tokenization_utils_base import PreTrainedTokenizerBase
|
||||
from ...utils import logging
|
||||
from ..processors.glue import glue_convert_examples_to_features, glue_output_modes, glue_processors
|
||||
from ..processors.utils import InputFeatures
|
||||
@@ -69,7 +66,7 @@ class GlueDataset(Dataset):
|
||||
def __init__(
|
||||
self,
|
||||
args: GlueDataTrainingArguments,
|
||||
tokenizer: PreTrainedTokenizer,
|
||||
tokenizer: PreTrainedTokenizerBase,
|
||||
limit_length: Optional[int] = None,
|
||||
mode: Union[str, Split] = Split.train,
|
||||
cache_dir: Optional[str] = None,
|
||||
@@ -93,12 +90,12 @@ class GlueDataset(Dataset):
|
||||
),
|
||||
)
|
||||
label_list = self.processor.get_labels()
|
||||
if args.task_name in ["mnli", "mnli-mm"] and tokenizer.__class__ in (
|
||||
RobertaTokenizer,
|
||||
RobertaTokenizerFast,
|
||||
XLMRobertaTokenizer,
|
||||
BartTokenizer,
|
||||
BartTokenizerFast,
|
||||
if args.task_name in ["mnli", "mnli-mm"] and tokenizer.__class__.__name__ in (
|
||||
"RobertaTokenizer",
|
||||
"RobertaTokenizerFast",
|
||||
"XLMRobertaTokenizer",
|
||||
"BartTokenizer",
|
||||
"BartTokenizerFast",
|
||||
):
|
||||
# HACK(label indices are swapped in RoBERTa pretrained model)
|
||||
label_list[1], label_list[2] = label_list[2], label_list[1]
|
||||
|
||||
Reference in New Issue
Block a user