Move test model folders (#17034)

* move test model folders (TODO: fix imports and others) * fix (potentially partially) imports (in model test modules) * fix (potentially partially) imports (in tokenization test modules) * fix (potentially partially) imports (in feature extraction test modules) * fix import utils.test_modeling_tf_core * fix path ../fixtures/ * fix imports about generation.test_generation_flax_utils * fix more imports * fix fixture path * fix get_test_dir * update module_to_test_file * fix get_tests_dir from wrong transformers.utils * update config.yml (CircleCI) * fix style * remove missing imports * update new model script * update check_repo * update SPECIAL_MODULE_TO_TEST_MAP * fix style * add __init__ * update self-scheduled * fix add_new_model scripts * check one way to get location back * python setup.py build install * fix import in test auto * update self-scheduled.yml * update slack notification script * Add comments about artifact names * fix for yolos Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
2022-05-03 14:42:02 +02:00
parent cd9274d010
commit 19420fd99e
408 changed files with 616 additions and 607 deletions
--- a/tests/models/herbert/init.py
+++ b/tests/models/herbert/init.py
--- a/tests/models/herbert/test_tokenization_herbert.py
+++ b/tests/models/herbert/test_tokenization_herbert.py
@@ -0,0 +1,128 @@
+# coding=utf-8
+# Copyright 2018 The Google AI Language Team Authors, Allegro.pl and The HuggingFace Inc. team.
+#
+# 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 json
+import os
+import unittest
+
+from transformers import HerbertTokenizer, HerbertTokenizerFast
+from transformers.models.herbert.tokenization_herbert import VOCAB_FILES_NAMES
+from transformers.testing_utils import get_tests_dir, require_tokenizers, slow
+
+from ...test_tokenization_common import TokenizerTesterMixin
+
+
+@require_tokenizers
+class HerbertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
+
+    tokenizer_class = HerbertTokenizer
+    rust_tokenizer_class = HerbertTokenizerFast
+    test_rust_tokenizer = True
+
+    def setUp(self):
+        super().setUp()
+
+        # Use a simpler test file without japanese/chinese characters
+        with open(f"{get_tests_dir()}/fixtures/sample_text_no_unicode.txt", encoding="utf-8") as f_data:
+            self._data = f_data.read().replace("\n\n", "\n").strip()
+
+        vocab = [
+            "<s>",
+            "</s>",
+            "l",
+            "o",
+            "w",
+            "e",
+            "r",
+            "s",
+            "t",
+            "i",
+            "d",
+            "n",
+            "w</w>",
+            "r</w>",
+            "t</w>",
+            "lo",
+            "low",
+            "er</w>",
+            "low</w>",
+            "lowest</w>",
+            "newer</w>",
+            "wider</w>",
+            ",</w>",
+            "<unk>",
+        ]
+        vocab_tokens = dict(zip(vocab, range(len(vocab))))
+        merges = ["l o 123", "lo w 1456", "e r</w> 1789", ""]
+
+        self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
+        self.merges_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["merges_file"])
+        with open(self.vocab_file, "w") as fp:
+            fp.write(json.dumps(vocab_tokens))
+        with open(self.merges_file, "w") as fp:
+            fp.write("\n".join(merges))
+
+    def get_input_output_texts(self, tokenizer):
+        input_text = "lower newer"
+        output_text = "lower newer"
+        return input_text, output_text
+
+    def test_full_tokenizer(self):
+        tokenizer = self.tokenizer_class(vocab_file=self.vocab_file, merges_file=self.merges_file)
+
+        text = "lower"
+        bpe_tokens = ["low", "er</w>"]
+        tokens = tokenizer.tokenize(text)
+        self.assertListEqual(tokens, bpe_tokens)
+
+        input_tokens = tokens + ["<unk>"]
+        input_bpe_tokens = [16, 17, 23]
+        self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
+
+    def test_rust_and_python_full_tokenizers(self):
+        if not self.test_rust_tokenizer:
+            return
+
+        tokenizer = self.get_tokenizer()
+        rust_tokenizer = self.get_rust_tokenizer()
+
+        sequence = "lower,newer"
+
+        tokens = tokenizer.tokenize(sequence)
+        rust_tokens = rust_tokenizer.tokenize(sequence)
+        self.assertListEqual(tokens, rust_tokens)
+
+        ids = tokenizer.encode(sequence, add_special_tokens=False)
+        rust_ids = rust_tokenizer.encode(sequence, add_special_tokens=False)
+        self.assertListEqual(ids, rust_ids)
+
+        rust_tokenizer = self.get_rust_tokenizer()
+        ids = tokenizer.encode(sequence)
+        rust_ids = rust_tokenizer.encode(sequence)
+        self.assertListEqual(ids, rust_ids)
+
+    @slow
+    def test_sequence_builders(self):
+        tokenizer = self.tokenizer_class.from_pretrained("allegro/herbert-base-cased")
+
+        text = tokenizer.encode("konstruowanie sekwencji", add_special_tokens=False)
+        text_2 = tokenizer.encode("konstruowanie wielu sekwencji", add_special_tokens=False)
+
+        encoded_sentence = tokenizer.build_inputs_with_special_tokens(text)
+        encoded_pair = tokenizer.build_inputs_with_special_tokens(text, text_2)
+
+        assert encoded_sentence == [0] + text + [2]
+        assert encoded_pair == [0] + text + [2] + text_2 + [2]