Ruonan Wang 5df31db773 LLM: fix accuracy issue of chatglm3 (#9830) ... * add attn mask for first token * fix * fix * change attn calculation * fix * fix * fix style * fix style		2024-01-05 10:52:05 +08:00
..
llm	LLM: fix accuracy issue of chatglm3 (#9830)	2024-01-05 10:52:05 +08:00