Travis Johnson d8663cb8c5 Fix bugs in mllama image processing (#36156) ... * fix: handle input_channel_dim == channels_last Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com> * fix: default PIL images to channels_last Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com> * Apply suggestions from code review Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com> * fixup from review batch Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com> * test: add 1x1 PIL image to ambiguous channel test Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com> * fix(mllama): avoid 0 dimension for image with impractical aspect ratio Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com> --------- Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com> Co-authored-by: Pavel Iakubovskii <qubvel@gmail.com>		2025-03-11 10:22:48 +01:00
..
__init__.py	Add MLLama (#33703)	2024-09-25 19:56:25 +02:00
test_image_processing_mllama.py	Fix bugs in mllama image processing (#36156)	2025-03-11 10:22:48 +01:00
test_modeling_mllama.py	Fix typos in tests (#36547)	2025-03-05 15:04:06 -08:00
test_processor_mllama.py	Chat template: update for processor (#35953)	2025-02-10 09:52:19 +01:00