ldwang 36ac14a566 Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3. ...

Signed-off-by: ldwang <ftgreat@gmail.com>

Former-commit-id: d1413dcec8a3b1d671f240b82a689c72b54d7b93

2024-01-24 14:43:16 +08:00

..

api

fix api

2024-01-21 19:15:27 +08:00

chat

finish agent

2024-01-21 01:47:33 +08:00

data

fix #2282 and update tool prompt

2024-01-22 22:27:30 +08:00

eval

format style

2024-01-20 20:15:56 +08:00

extras

add orion models

2024-01-22 21:26:53 +08:00

hparams

fix #2282 and update tool prompt

2024-01-22 22:27:30 +08:00

model

Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3.

2024-01-24 14:43:16 +08:00

train

Update tuner.py

2024-01-21 12:39:38 +08:00

webui

format

2024-01-21 12:34:17 +08:00

__init__.py

fix api

2024-01-21 19:15:27 +08:00