mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-16 11:08:23 +06:00
368b649af6
* Rebase ESM PR and update all file formats * Fix test relative imports * Add __init__.py to the test dir * Disable gradient checkpointing * Remove references to TFESM... FOR NOW >:| * Remove completed TODOs from tests * Convert docstrings to mdx, fix-copies from BERT * fix-copies for the README and index * Update ESM's __init__.py to the modern format * Add to _toctree.yml * Ensure we correctly copy the pad_token_id from the original ESM model * Ensure we correctly copy the pad_token_id from the original ESM model * Tiny grammar nitpicks * Make the layer norm after embeddings an optional flag * Make the layer norm after embeddings an optional flag * Update the conversion script to handle other model classes * Remove token_type_ids entirely, fix attention_masking and add checks to convert_esm.py * Break the copied from link from BertModel.forward to remove token_type_ids * Remove debug array saves * Begin ESM-2 porting * Add a hacky workaround for the precision issue in original repo * Code cleanup * Remove unused checkpoint conversion code * Remove unused checkpoint conversion code * Fix copyright notices * Get rid of all references to the TF weights conversion * Remove token_type_ids from the tests * Fix test code * Update src/transformers/__init__.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/__init__.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update README.md Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Add credit * Remove _ args and __ kwargs in rotary embedding * Assertively remove asserts * Replace einsum with torch.outer() * Fix docstring formatting * Remove assertions in tokenization * Add paper citation to ESMModel docstring * Move vocab list to single line * Remove ESMLayer from init * Add Facebook copyrights * Clean up RotaryEmbedding docstring * Fix docstring formatting * Fix docstring for config object * Add explanation for new config methods * make fix-copies * Rename all the ESM- classes to Esm- * Update conversion script to allow pushing to hub * Update tests to point at my repo for now * Set config properly for tests * Remove the gross hack that forced loss of precision in inv_freq and instead copy the data from the model being converted * make fixup * Update expected values for slow tests * make fixup * Remove EsmForCausalLM for now * Remove EsmForCausalLM for now * Fix padding idx test * Updated README and docs with ESM-1b and ESM-2 separately (#19221) * Updated README and docs with ESM-1b and ESM-2 separately * Update READMEs, longer entry with 3 citations * make fix-copies Co-authored-by: Your Name <you@example.com> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> Co-authored-by: Tom Sercu <tsercu@fb.com> Co-authored-by: Your Name <you@example.com>
92 lines
3.6 KiB
Python
92 lines
3.6 KiB
Python
# coding=utf-8
|
|
# Copyright 2021 The HuggingFace Team. All rights reserved.
|
|
#
|
|
# 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 os
|
|
import tempfile
|
|
import unittest
|
|
from typing import List
|
|
|
|
from transformers.models.esm.tokenization_esm import VOCAB_FILES_NAMES, EsmTokenizer
|
|
from transformers.testing_utils import require_tokenizers
|
|
from transformers.tokenization_utils import PreTrainedTokenizer
|
|
from transformers.tokenization_utils_base import PreTrainedTokenizerBase
|
|
|
|
|
|
@require_tokenizers
|
|
class ESMTokenizationTest(unittest.TestCase):
|
|
tokenizer_class = EsmTokenizer
|
|
|
|
def setUp(self):
|
|
super().setUp()
|
|
self.tmpdirname = tempfile.mkdtemp()
|
|
# fmt: off
|
|
vocab_tokens: List[str] = ["<cls>", "<pad>", "<eos>", "<unk>", "L", "A", "G", "V", "S", "E", "R", "T", "I", "D", "P", "K", "Q", "N", "F", "Y", "M", "H", "W", "C", "X", "B", "U", "Z", "O", ".", "-", "<null_1>", "<mask>"] # noqa: E501
|
|
# fmt: on
|
|
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
|
|
with open(self.vocab_file, "w", encoding="utf-8") as vocab_writer:
|
|
vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
|
|
|
|
def get_tokenizers(self, **kwargs) -> List[PreTrainedTokenizerBase]:
|
|
return [self.get_tokenizer(**kwargs)]
|
|
|
|
def get_tokenizer(self, **kwargs) -> PreTrainedTokenizer:
|
|
return self.tokenizer_class.from_pretrained(self.tmpdirname, **kwargs)
|
|
|
|
def test_tokenizer_single_example(self):
|
|
tokenizer = self.tokenizer_class(self.vocab_file)
|
|
|
|
tokens = tokenizer.tokenize("LAGVS")
|
|
self.assertListEqual(tokens, ["L", "A", "G", "V", "S"])
|
|
self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [4, 5, 6, 7, 8])
|
|
|
|
def test_tokenizer_encode_single(self):
|
|
tokenizer = self.tokenizer_class(self.vocab_file)
|
|
|
|
seq = "LAGVS"
|
|
self.assertListEqual(tokenizer.encode(seq), [0, 4, 5, 6, 7, 8, 2])
|
|
|
|
def test_tokenizer_call_no_pad(self):
|
|
tokenizer = self.tokenizer_class(self.vocab_file)
|
|
|
|
seq_batch = ["LAGVS", "WCB"]
|
|
tokens_batch = tokenizer(seq_batch, padding=False)["input_ids"]
|
|
|
|
self.assertListEqual(tokens_batch, [[0, 4, 5, 6, 7, 8, 2], [0, 22, 23, 25, 2]])
|
|
|
|
def test_tokenizer_call_pad(self):
|
|
tokenizer = self.tokenizer_class(self.vocab_file)
|
|
|
|
seq_batch = ["LAGVS", "WCB"]
|
|
tokens_batch = tokenizer(seq_batch, padding=True)["input_ids"]
|
|
|
|
self.assertListEqual(tokens_batch, [[0, 4, 5, 6, 7, 8, 2], [0, 22, 23, 25, 2, 1, 1]])
|
|
|
|
def test_tokenize_special_tokens(self):
|
|
"""Test `tokenize` with special tokens."""
|
|
tokenizers = self.get_tokenizers(fast=True)
|
|
for tokenizer in tokenizers:
|
|
with self.subTest(f"{tokenizer.__class__.__name__}"):
|
|
SPECIAL_TOKEN_1 = "<unk>"
|
|
SPECIAL_TOKEN_2 = "<mask>"
|
|
|
|
token_1 = tokenizer.tokenize(SPECIAL_TOKEN_1)
|
|
token_2 = tokenizer.tokenize(SPECIAL_TOKEN_2)
|
|
|
|
self.assertEqual(len(token_1), 1)
|
|
self.assertEqual(len(token_2), 1)
|
|
self.assertEqual(token_1[0], SPECIAL_TOKEN_1)
|
|
self.assertEqual(token_2[0], SPECIAL_TOKEN_2)
|