hoshi-hiyouga 0af4d834ef [data] optimize qwen3 loss computation (#7923)

2025-04-30 16:18:00 +08:00

..

components

[data] optimize qwen3 loss computation (#7923)

2025-04-30 16:18:00 +08:00

__init__.py

rename package

2024-05-16 18:39:08 +08:00

chatter.py

[data] optimize qwen3 loss computation (#7923)

2025-04-30 16:18:00 +08:00

common.py

[misc] upgrade format to py39 (#7256)

2025-03-12 00:08:41 +08:00

control.py

[model] add qwen3 (#7885)

2025-04-29 09:34:05 +08:00

css.py

[webui] update css (#6985)

2025-02-18 18:27:57 +08:00

engine.py

[misc] upgrade format to py39 (#7256)

2025-03-12 00:08:41 +08:00

interface.py

[model] fix kv cache (#7564)

2025-04-01 23:07:46 +08:00

locales.py

[data] optimize qwen3 loss computation (#7923)

2025-04-30 16:18:00 +08:00

manager.py

[misc] upgrade format to py39 (#7256)

2025-03-12 00:08:41 +08:00

runner.py

[breaking] bump transformers to 4.45.0 & improve ci (#7746)

2025-04-17 02:36:48 +08:00