Add barthez model (#8393)

* Add init barthez * Add barthez model, tokenizer and docs BARThez is a pre-trained french seq2seq model that uses BART objective. * Apply suggestions from code review docs typos Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Add license * Change URLs scheme * Remove barthez model keep tokenizer * Fix style * Fix quality * Update tokenizer * Add fast tokenizer * Add fast tokenizer test Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2020-11-27 18:31:42 +01:00
parent b0f2dbc594
commit 81fe0bf085
13 changed files with 799 additions and 34 deletions
--- a/tests/test_tokenization_barthez.py
+++ b/tests/test_tokenization_barthez.py
@@ -0,0 +1,79 @@
+# coding=utf-8
+# Copyright 2020 Ecole Polytechnique and 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 unittest
+
+from transformers import BarthezTokenizer, BarthezTokenizerFast, BatchEncoding
+from transformers.testing_utils import require_sentencepiece, require_tokenizers, require_torch
+
+from .test_tokenization_common import TokenizerTesterMixin
+
+
+@require_tokenizers
+@require_sentencepiece
+class BarthezTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
+
+    tokenizer_class = BarthezTokenizer
+    rust_tokenizer_class = BarthezTokenizerFast
+    test_rust_tokenizer = True
+
+    def setUp(self):
+        super().setUp()
+
+        tokenizer = BarthezTokenizer.from_pretrained("moussaKam/mbarthez")
+        tokenizer.save_pretrained(self.tmpdirname)
+        self.tokenizer = tokenizer
+
+    @require_torch
+    def test_prepare_seq2seq_batch(self):
+        src_text = ["A long paragraph for summarization.", "Another paragraph for summarization."]
+        tgt_text = [
+            "Summary of the text.",
+            "Another summary.",
+        ]
+        expected_src_tokens = [0, 57, 3018, 70307, 91, 2]
+
+        batch = self.tokenizer.prepare_seq2seq_batch(
+            src_text, tgt_texts=tgt_text, max_length=len(expected_src_tokens), return_tensors="pt"
+        )
+        self.assertIsInstance(batch, BatchEncoding)
+
+        self.assertEqual((2, 6), batch.input_ids.shape)
+        self.assertEqual((2, 6), batch.attention_mask.shape)
+        result = batch.input_ids.tolist()[0]
+        self.assertListEqual(expected_src_tokens, result)
+
+    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 = "I was born in 92000, and this is falsé."
+
+        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)