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

30
tests/models/mllama/test_processor_mllama.py
View File

@@ -36,21 +36,23 @@ if is_vision_available():
class MllamaProcessorTest(ProcessorTesterMixin, unittest.TestCase):
processor_class = MllamaProcessor
def setUp(self):
self.checkpoint = "hf-internal-testing/mllama-11b"
processor = MllamaProcessor.from_pretrained(self.checkpoint)
self.image1 = Image.new("RGB", (224, 220))
self.image2 = Image.new("RGB", (512, 128))
self.image_token = processor.image_token
self.image_token_id = processor.image_token_id
self.pad_token_id = processor.tokenizer.pad_token_id
self.bos_token = processor.bos_token
self.bos_token_id = processor.tokenizer.bos_token_id
self.tmpdirname = tempfile.mkdtemp()
processor.save_pretrained(self.tmpdirname)
@classmethod
def setUpClass(cls):
cls.checkpoint = "hf-internal-testing/mllama-11b"
processor = MllamaProcessor.from_pretrained(cls.checkpoint)
cls.image1 = Image.new("RGB", (224, 220))
cls.image2 = Image.new("RGB", (512, 128))
cls.image_token = processor.image_token
cls.image_token_id = processor.image_token_id
cls.pad_token_id = processor.tokenizer.pad_token_id
cls.bos_token = processor.bos_token
cls.bos_token_id = processor.tokenizer.bos_token_id
cls.tmpdirname = tempfile.mkdtemp()
processor.save_pretrained(cls.tmpdirname)
def tearDown(self):
shutil.rmtree(self.tmpdirname)
@classmethod
def tearDownClass(cls):
shutil.rmtree(cls.tmpdirname, ignore_errors=True)
def prepare_processor_dict(self):
return {"chat_template": "{% for message in messages %}{% if loop.index0 == 0 %}{{ bos_token }}{% endif %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' }}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<|image|>' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{ '<|eot_id|>' }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"} # fmt: skip