SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

🚨 🚨 Setup -> setupclass conversion (#37282)

Browse Source 
* More limited setup -> setupclass conversion

* make fixup

* Trigger tests

* Fixup UDOP

* Missed a spot

* tearDown -> tearDownClass where appropriate

* Couple more class fixes

* Fixups for UDOP and VisionTextDualEncoder

* Ignore errors when removing the tmpdir, in case it already got cleaned up somewhere

* CLIP fixes

* More correct classmethods

* Wav2Vec2Bert fixes

* More methods become static

* More class methods

* More class methods

* Revert changes for integration tests / modeling files

* Use a different tempdir for tests that actually write to it

* Remove addClassCleanup and just use teardownclass

* Remove changes in modeling files

* Cleanup get_processor_dict() for got_ocr2

* Fix regression on Wav2Vec2BERT test that was masked by this before

* Rework tests that modify the tmpdir

* make fix-copies

* revert clvp modeling test changes

* Fix CLIP processor test

* make fix-copies
This commit is contained in:
Matt
2025-04-08 17:15:37 +01:00
committed by GitHub
parent c15a7adb28
commit 4d0de5f73a
49 changed files with 740 additions and 574 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tests/models/gemma3/test_processing_gemma3.py
View File

@@ -34,8 +34,9 @@ SAMPLE_VOCAB = get_tests_dir("fixtures/test_sentencepiece.model")
class Gemma3ProcessorTest(ProcessorTesterMixin, unittest.TestCase):
processor_class = Gemma3Processor
def setUp(self):
self.tmpdirname = tempfile.mkdtemp()
@classmethod
def setUpClass(cls):
cls.tmpdirname = tempfile.mkdtemp()
gemma3_image_processor_kwargs = {
"do_pan_and_scan": True,
"pan_and_scan_min_crop_size": 256,
@@ -52,15 +53,17 @@ class Gemma3ProcessorTest(ProcessorTesterMixin, unittest.TestCase):
"eoi_token": "<end_of_image>",
}
tokenizer = GemmaTokenizer(SAMPLE_VOCAB, keep_accents=True, extra_special_tokens=extra_special_tokens)
processor_kwargs = self.prepare_processor_dict()
processor_kwargs = cls.prepare_processor_dict()
processor = Gemma3Processor(image_processor=image_processor, tokenizer=tokenizer, **processor_kwargs)
processor.save_pretrained(self.tmpdirname)
processor.save_pretrained(cls.tmpdirname)
def tearDown(self):
shutil.rmtree(self.tmpdirname)
@classmethod
def tearDownClass(cls):
shutil.rmtree(cls.tmpdirname, ignore_errors=True)
# TODO: raushan or arthur: add the real chat template
def prepare_processor_dict(self):
@staticmethod
def prepare_processor_dict():
return {
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n", "image_seq_length": 3,
} # fmt: skip