transformers/tests/models/aria
youngrok cha acded47fe7
[llava] one pixel is missing from padding when length is odd (#37819)
* [fix] one pixel should be added when length is odd

* [fix] add vision_aspect_ratio args & typo

* [fix] style

* [fix] do not fix fast file directly

* [fix] convert using modular

* remove duplicate codes

* match unpad logic with pad logic

* test odd-sized images for llava & aria

* test unpad odd-sized padding for llava family

* fix style

* add kwarg to onvision modular

* move vision_aspect_ratio from image_processor to processor
(llava_onevision)
2025-05-06 13:11:26 +02:00
..
__init__.py Add Aria (#34157) 2024-12-06 12:17:34 +01:00
test_image_processing_aria.py [llava] one pixel is missing from padding when length is odd (#37819) 2025-05-06 13:11:26 +02:00
test_modeling_aria.py Skip all AriaForConditionalGenerationIntegrationTest on T4 (#37746) 2025-04-24 14:11:56 +02:00
test_processor_aria.py [vlm] adjust max length for special tokens (#37342) 2025-04-16 20:49:20 +02:00