Remove static pretrained maps from the library's internals (#29112)

* [test_all] Remove static pretrained maps from the library's internals

* Deprecate archive maps instead of removing them

* Revert init changes

* [test_all] Deprecate instead of removing

* [test_all] PVT v2 support

* [test_all] Tests should all pass

* [test_all] Style

* Address review comments

* Update src/transformers/models/deprecated/_archive_maps.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/models/deprecated/_archive_maps.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* [test_all] trigger tests

* [test_all] LLAVA

* [test_all] Bad rebase

---------

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
This commit is contained in:
Lysandre Debut
2024-03-25 10:33:38 +01:00
committed by GitHub
parent 76a33a1092
commit 39114c0383
842 changed files with 4608 additions and 8613 deletions

View File

@@ -25,8 +25,6 @@ import pytest
import transformers
from transformers import (
BERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP,
AutoTokenizer,
BertConfig,
BertTokenizer,
@@ -72,13 +70,13 @@ class AutoTokenizerTest(unittest.TestCase):
@slow
def test_tokenizer_from_pretrained(self):
for model_name in (x for x in BERT_PRETRAINED_CONFIG_ARCHIVE_MAP.keys() if "japanese" not in x):
for model_name in {"google-bert/bert-base-uncased", "google-bert/bert-base-cased"}:
tokenizer = AutoTokenizer.from_pretrained(model_name)
self.assertIsNotNone(tokenizer)
self.assertIsInstance(tokenizer, (BertTokenizer, BertTokenizerFast))
self.assertGreater(len(tokenizer), 0)
for model_name in GPT2_PRETRAINED_CONFIG_ARCHIVE_MAP.keys():
for model_name in ["openai-community/gpt2", "openai-community/gpt2-medium"]:
tokenizer = AutoTokenizer.from_pretrained(model_name)
self.assertIsNotNone(tokenizer)
self.assertIsInstance(tokenizer, (GPT2Tokenizer, GPT2TokenizerFast))