Ashwin Bharambe 35aac86997 update generate prompt format		2025-04-07 14:59:04 -07:00
..
llama3	revert some unintentional changes by copying source of truth to llama-models	2025-04-07 11:01:24 -07:00
llama3_1	feat: introduce llama4 support (#1877)	2025-04-05 11:53:35 -07:00
llama3_2	several fixes	2025-04-07 10:31:20 -07:00
llama3_3	chore: remove dependency on llama_models completely (#1344)	2025-03-01 12:48:08 -08:00
llama4	rename quant types to use _mixed naming	2025-04-07 12:57:58 -07:00
resources	feat: introduce llama4 support (#1877)	2025-04-05 11:53:35 -07:00
__init__.py	feat: introduce llama4 support (#1877)	2025-04-05 11:53:35 -07:00
checkpoint.py	several fixes	2025-04-07 10:31:20 -07:00
datatypes.py	revert some unintentional changes by copying source of truth to llama-models	2025-04-07 11:01:24 -07:00
hadamard_utils.py	refactor: move all llama code to models/llama out of meta reference	2025-04-06 22:42:32 -07:00
prompt_format.py	update generate prompt format	2025-04-07 14:59:04 -07:00
quantize_impls.py	refactor: move all llama code to models/llama out of meta reference	2025-04-06 22:42:32 -07:00
sku_list.py	several fixes	2025-04-07 10:31:20 -07:00
sku_types.py	several fixes	2025-04-07 10:31:20 -07:00