mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-06 22:30:09 +06:00
ba8c4d0ac0
* 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>
69 lines
3.0 KiB
Python
69 lines
3.0 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 The Google AI Language Team Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
|
|
import unittest
|
|
|
|
from transformers import is_torch_available
|
|
from transformers.testing_utils import require_sentencepiece, require_tokenizers, slow
|
|
|
|
|
|
if is_torch_available():
|
|
import torch
|
|
|
|
from transformers import XLMRobertaModel
|
|
|
|
|
|
@require_sentencepiece
|
|
@require_tokenizers
|
|
class XLMRobertaModelIntegrationTest(unittest.TestCase):
|
|
@slow
|
|
def test_xlm_roberta_base(self):
|
|
model = XLMRobertaModel.from_pretrained("xlm-roberta-base", return_dict=True)
|
|
input_ids = torch.tensor([[0, 581, 10269, 83, 99942, 136, 60742, 23, 70, 80583, 18276, 2]])
|
|
# The dog is cute and lives in the garden house
|
|
|
|
expected_output_shape = torch.Size((1, 12, 768)) # batch_size, sequence_length, embedding_vector_dim
|
|
expected_output_values_last_dim = torch.tensor(
|
|
[[-0.0101, 0.1218, -0.0803, 0.0801, 0.1327, 0.0776, -0.1215, 0.2383, 0.3338, 0.3106, 0.0300, 0.0252]]
|
|
)
|
|
# xlmr = torch.hub.load('pytorch/fairseq', 'xlmr.base')
|
|
# xlmr.eval()
|
|
# expected_output_values_last_dim = xlmr.extract_features(input_ids[0])[:, :, -1]
|
|
|
|
output = model(input_ids)["last_hidden_state"].detach()
|
|
self.assertEqual(output.shape, expected_output_shape)
|
|
# compare the actual values for a slice of last dim
|
|
self.assertTrue(torch.allclose(output[:, :, -1], expected_output_values_last_dim, atol=1e-3))
|
|
|
|
@slow
|
|
def test_xlm_roberta_large(self):
|
|
model = XLMRobertaModel.from_pretrained("xlm-roberta-large", return_dict=True)
|
|
input_ids = torch.tensor([[0, 581, 10269, 83, 99942, 136, 60742, 23, 70, 80583, 18276, 2]])
|
|
# The dog is cute and lives in the garden house
|
|
|
|
expected_output_shape = torch.Size((1, 12, 1024)) # batch_size, sequence_length, embedding_vector_dim
|
|
expected_output_values_last_dim = torch.tensor(
|
|
[[-0.0699, -0.0318, 0.0705, -0.1241, 0.0999, -0.0520, 0.1004, -0.1838, -0.4704, 0.1437, 0.0821, 0.0126]]
|
|
)
|
|
# xlmr = torch.hub.load('pytorch/fairseq', 'xlmr.large')
|
|
# xlmr.eval()
|
|
# expected_output_values_last_dim = xlmr.extract_features(input_ids[0])[:, :, -1]
|
|
|
|
output = model(input_ids)["last_hidden_state"].detach()
|
|
self.assertEqual(output.shape, expected_output_shape)
|
|
# compare the actual values for a slice of last dim
|
|
self.assertTrue(torch.allclose(output[:, :, -1], expected_output_values_last_dim, atol=1e-3))
|