hoshi-hiyouga ff8ef6f52c [model] fix mllama any image (#6637) ...

* fix mllama any image

* reorder classes

Former-commit-id: 1242a1c4b4a465c06363fdc59302e80e5c4c96e6

2025-01-14 16:47:58 +08:00

..

api

Support Mistral format tools

2024-12-17 19:13:26 +00:00

chat

[inference] fix stop token for object detection (#6624)

2025-01-13 21:34:20 +08:00

data

[model] fix mllama any image (#6637)

2025-01-14 16:47:58 +08:00

eval

Add trust_remote_code parameter and remove True

2024-12-17 12:25:12 +00:00

extras

Support new features of MiniCPM-V (#6626)

2025-01-14 00:26:19 +08:00

hparams

pin vllm version to 0.6.5 (#6629)

2025-01-14 02:44:02 +08:00

model

Support new features of MiniCPM-V (#6626)

2025-01-14 00:26:19 +08:00

train

[inference] fix stop token for object detection (#6624)

2025-01-13 21:34:20 +08:00

webui

[inference] fix stop token for object detection (#6624)

2025-01-13 21:34:20 +08:00

__init__.py

generalized packing & fix #6343

2024-12-17 10:26:19 +00:00

cli.py

refactor ray integration, support save ckpt

2025-01-07 09:39:10 +00:00

launcher.py

fix mixed mm inputs and rlhf-v

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