hoshi-hiyouga ceb701c2d4 Merge pull request #5909 from hiyouga/hiyouga/dev2 ...

[data] support auto convert for single image, add image_dir argument

Former-commit-id: ced43fa0c84f7d0792694721d2c5e572c0d0e718

2024-11-02 13:43:04 +08:00

..

api

support multiimage inference

2024-11-01 07:25:20 +00:00

chat

add examples

2024-11-01 08:41:54 +00:00

data

Merge pull request #5909 from hiyouga/hiyouga/dev2

2024-11-02 13:43:04 +08:00

eval

use pre-commit

2024-10-29 09:07:46 +00:00

extras

fix incorrect loss value for vlms

2024-10-30 08:56:46 +00:00

hparams

fix #5883

2024-11-02 13:06:34 +08:00

model

Merge pull request #5907 from hiyouga/hiyouga/dev

2024-11-02 13:42:53 +08:00

train

update tests

2024-11-02 12:41:44 +08:00

webui

support multiimage inference

2024-11-01 07:25:20 +00:00

__init__.py

fix incorrect loss value for vlms

2024-10-30 08:56:46 +00:00

cli.py

update tests

2024-11-02 12:41:44 +08:00

launcher.py

fix mixed mm inputs and rlhf-v

2024-09-01 20:52:47 +08:00