mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 21:30:07 +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>
56 lines
2.0 KiB
Python
56 lines
2.0 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, require_torch, slow, torch_device
|
|
|
|
|
|
if is_torch_available():
|
|
import torch
|
|
|
|
from transformers import CamembertModel
|
|
|
|
|
|
@require_torch
|
|
@require_sentencepiece
|
|
@require_tokenizers
|
|
class CamembertModelIntegrationTest(unittest.TestCase):
|
|
@slow
|
|
def test_output_embeds_base_model(self):
|
|
model = CamembertModel.from_pretrained("camembert-base", return_dict=True)
|
|
model.to(torch_device)
|
|
|
|
input_ids = torch.tensor(
|
|
[[5, 121, 11, 660, 16, 730, 25543, 110, 83, 6]],
|
|
device=torch_device,
|
|
dtype=torch.long,
|
|
) # J'aime le camembert !
|
|
output = model(input_ids)["last_hidden_state"]
|
|
expected_shape = torch.Size((1, 10, 768))
|
|
self.assertEqual(output.shape, expected_shape)
|
|
# compare the actual values for a slice.
|
|
expected_slice = torch.tensor(
|
|
[[[-0.0254, 0.0235, 0.1027], [0.0606, -0.1811, -0.0418], [-0.1561, -0.1127, 0.2687]]],
|
|
device=torch_device,
|
|
dtype=torch.float,
|
|
)
|
|
# camembert = torch.hub.load('pytorch/fairseq', 'camembert.v0')
|
|
# camembert.eval()
|
|
# expected_slice = roberta.model.forward(input_ids)[0][:, :3, :3].detach()
|
|
|
|
self.assertTrue(torch.allclose(output[:, :3, :3], expected_slice, atol=1e-4))
|