SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Dependencies|tokenizers] Make both SentencePiece and Tokenizers optional dependencies (#7659)

Browse Source 
* 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
2020-10-18 20:51:24 +02:00
committed by GitHub
parent c65863ce53
commit ba8c4d0ac0
140 changed files with 6551 additions and 3961 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
tests/test_tokenization_roberta.py
View File

@@ -18,16 +18,19 @@ import json
import os
import unittest
from transformers.testing_utils import slow
from transformers.tokenization_roberta import VOCAB_FILES_NAMES, AddedToken, RobertaTokenizer, RobertaTokenizerFast
from transformers import AddedToken, RobertaTokenizer, RobertaTokenizerFast
from transformers.testing_utils import require_tokenizers, slow
from transformers.tokenization_roberta import VOCAB_FILES_NAMES
from .test_tokenization_common import TokenizerTesterMixin
@require_tokenizers
class RobertaTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
tokenizer_class = RobertaTokenizer
rust_tokenizer_class = RobertaTokenizerFast
test_rust_tokenizer = True
from_pretrained_kwargs = {"cls_token": "<s>"}
def setUp(self):
super().setUp()
@@ -158,3 +161,38 @@ class RobertaTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
mask_loc = encoded.index(mask_ind)
first_char = tokenizer.convert_ids_to_tokens(encoded[mask_loc + 1])[0]
self.assertNotEqual(first_char, space_encoding)
def test_pretokenized_inputs(self):
pass
def test_embeded_special_tokens(self):
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest("{} ({})".format(tokenizer.__class__.__name__, pretrained_name)):
tokenizer_r = self.rust_tokenizer_class.from_pretrained(pretrained_name, **kwargs)
tokenizer_p = self.tokenizer_class.from_pretrained(pretrained_name, **kwargs)
sentence = "A, <mask> AllenNLP sentence."
tokens_r = tokenizer_r.encode_plus(sentence, add_special_tokens=True, return_token_type_ids=True)
tokens_p = tokenizer_p.encode_plus(sentence, add_special_tokens=True, return_token_type_ids=True)
# token_type_ids should put 0 everywhere
self.assertEqual(sum(tokens_r["token_type_ids"]), sum(tokens_p["token_type_ids"]))
# attention_mask should put 1 everywhere, so sum over length should be 1
self.assertEqual(
sum(tokens_r["attention_mask"]) / len(tokens_r["attention_mask"]),
sum(tokens_p["attention_mask"]) / len(tokens_p["attention_mask"]),
)
tokens_r_str = tokenizer_r.convert_ids_to_tokens(tokens_r["input_ids"])
tokens_p_str = tokenizer_p.convert_ids_to_tokens(tokens_p["input_ids"])
# Rust correctly handles the space before the mask while python doesnt
self.assertSequenceEqual(tokens_p["input_ids"], [0, 250, 6, 50264, 3823, 487, 21992, 3645, 4, 2])
self.assertSequenceEqual(tokens_r["input_ids"], [0, 250, 6, 50264, 3823, 487, 21992, 3645, 4, 2])
self.assertSequenceEqual(
tokens_p_str, ["<s>", "A", ",", "<mask>", "ĠAllen", "N", "LP", "Ġsentence", ".", "</s>"]
)
self.assertSequenceEqual(
tokens_r_str, ["<s>", "A", ",", "<mask>", "ĠAllen", "N", "LP", "Ġsentence", ".", "</s>"]
)