Qiyuan Gong d8808cc2e3 Mistral apply_rotary_pos_emb_no_cache_xpu use rope_theta from config (#11747) ... mistral-7B-instruct-v0.2 and mistral-7B-instruct-v0.1 use different rope_theta (0.2 is 1e, 0.1 is 1e5). Pass self.config.rope_theta to apply_rotary_pos_emb_no_cache_xpu to avoid output difference.		2024-08-09 10:35:51 +08:00
..
llm	Mistral apply_rotary_pos_emb_no_cache_xpu use rope_theta from config (#11747)	2024-08-09 10:35:51 +08:00