mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-05 22:00:09 +06:00
1670be4bde
* Adding Llama FastTokenizer support. - Requires https://github.com/huggingface/tokenizers/pull/1183 version - Only support byte_fallback for llama, raise otherwise (safety net). - Lots of questions are special tokens How to test: ```python from transformers.convert_slow_tokenizer import convert_slow_tokenizer from transformers import AutoTokenizer from tokenizers import Tokenizer tokenizer = AutoTokenizer.from_pretrained("huggingface/llama-7b") if False: new_tokenizer = Tokenizer.from_file("tok.json") else: new_tokenizer = convert_slow_tokenizer(tokenizer) new_tokenizer.save("tok.json") strings = [ "This is a test", "生活的真谛是", "生活的真谛是[MASK]。", # XXX: This one is problematic because of special tokens # "<s> Something something", ] for string in strings: encoded = tokenizer(string)["input_ids"] encoded2 = new_tokenizer.encode(string).ids assert encoded == encoded2, f"{encoded} != {encoded2}" decoded = tokenizer.decode(encoded) decoded2 = new_tokenizer.decode(encoded2) assert decoded.strip() == decoded2, f"{repr(decoded)} != {repr(decoded2)}" ``` The converter + some test script. The test script. Tmp save. Adding Fast tokenizer + tests. Adding the tokenization tests. Correct combination. Small fix. Fixing tests. Fixing with latest update. Rebased. fix copies + normalized added tokens + copies. Adding doc. TMP. Doc + split files. Doc. Versions + try import. Fix Camembert + warnings -> Error. Fix by ArthurZucker. Not a decorator. * Fixing comments. * Adding more to docstring. * Doc rewriting.
34 lines
1.3 KiB
Python
34 lines
1.3 KiB
Python
import unittest
|
|
import warnings
|
|
from dataclasses import dataclass
|
|
|
|
from transformers.convert_slow_tokenizer import SpmConverter
|
|
from transformers.testing_utils import get_tests_dir
|
|
|
|
|
|
@dataclass
|
|
class FakeOriginalTokenizer:
|
|
vocab_file: str
|
|
|
|
|
|
class ConvertSlowTokenizerTest(unittest.TestCase):
|
|
def test_spm_converter_bytefallback_warning(self):
|
|
spm_model_file_without_bytefallback = get_tests_dir("fixtures/test_sentencepiece.model")
|
|
spm_model_file_with_bytefallback = get_tests_dir("fixtures/test_sentencepiece_with_bytefallback.model")
|
|
|
|
original_tokenizer_without_bytefallback = FakeOriginalTokenizer(vocab_file=spm_model_file_without_bytefallback)
|
|
|
|
with warnings.catch_warnings(record=True) as w:
|
|
_ = SpmConverter(original_tokenizer_without_bytefallback)
|
|
self.assertEqual(len(w), 0)
|
|
|
|
original_tokenizer_with_bytefallback = FakeOriginalTokenizer(vocab_file=spm_model_file_with_bytefallback)
|
|
|
|
with self.assertRaises(RuntimeError) as cm:
|
|
_ = SpmConverter(original_tokenizer_with_bytefallback)
|
|
self.assertIn(
|
|
"The sentencepiece tokenizer that you are converting to a fast tokenizer uses the byte fallback option"
|
|
" which is not implemented in the fast tokenizers.",
|
|
str(cm.exception),
|
|
)
|