6 Commits

Author	SHA1	Message	Date
Ross Wightman	284e4ea7a9	Improve type handling for arange & rel pos embeds, keep calculations in float32 until application (may change to apply in float32 in future). Prevent arange type hijacking by DeepSpeed Zero	2024-01-26 14:17:54 -08:00
Ross Wightman	1f4512fca3	Support dynamic_resize in eva.py models	2023-08-27 15:58:35 -07:00
Ross Wightman	aef6e562e4	Add onnx utils and export code, tweak padding and conv2d_same for better dynamic export with recent PyTorch	2023-04-11 17:03:57 -07:00
Ross Wightman	4d135421a3	Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models	2023-04-07 20:27:23 -07:00
Ross Wightman	3863d63516	Adding EVA02 weights and model defs, move beit based eva_giant to same eva.py file. Cleanup rotary pos, add lang oriented freq bands to be compat with eva design choice. Fix #1738	2023-03-27 17:16:07 -07:00
Ross Wightman	9a51e4ea2e	Add FlexiViT models and weights, refactoring, push more weights ... * push all vision_transformer*.py weights to HF hub * finalize more pretrained tags for pushed weights * refactor pos_embed files and module locations, move some pos embed modules to layers * tweak hf hub helpers to aid bulk uploading and updating	2022-12-22 17:23:09 -08:00