Tom Aarsen 05ea7b79e6 Refactor: Use Llama RoPE implementation for Falcon (#26933) ... * Use Llama RoPE implementation for Falcon + Add copy functionalities * Use standard cache format for Falcon * Simplify apply_rotary_pos_emb, copy from Llama * Remove unnecessary cache conversion test We don't need to convert any caches anymore! * Resolve copy complaint		2023-11-03 11:05:55 +00:00
..
__init__.py	Falcon port (#24523)	2023-07-11 13:36:31 +01:00
test_modeling_falcon.py	Refactor: Use Llama RoPE implementation for Falcon (#26933)	2023-11-03 11:05:55 +00:00