cyflhn 03ba4bc760 fix error with xinference tool calling with qwen2-instruct and add timeout retry setttings for xinference (#11012) 8 mēneši atpakaļ
..
_assets d069c668f8 Model Runtime (#1858) 1 gadu atpakaļ
llm 03ba4bc760 fix error with xinference tool calling with qwen2-instruct and add timeout retry setttings for xinference (#11012) 8 mēneši atpakaļ
rerank 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mēneši atpakaļ
speech2text 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mēneši atpakaļ
text_embedding 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mēneši atpakaļ
tts 1e829ceaf3 chore: format get_customizable_model_schema return value (#9335) 9 mēneši atpakaļ
__init__.py d069c668f8 Model Runtime (#1858) 1 gadu atpakaļ
xinference.py d069c668f8 Model Runtime (#1858) 1 gadu atpakaļ
xinference.yaml 03ba4bc760 fix error with xinference tool calling with qwen2-instruct and add timeout retry setttings for xinference (#11012) 8 mēneši atpakaļ
xinference_helper.py 77aef9ff1d refactor: optimize the calculation of rerank threshold and the logic for forbidden characters in model_uid (#8879) 10 mēneši atpakaļ