neteroster
69 天前
> 相同的消息必须有相同的回复,违反了这点就意味着模型有所变化。
错误的。LLM 生成最后有采样步骤会引入随机性。即使贪婪采样,现代 LLM 推理框架在性能上的一些优化措施也会导致几乎丧失稳定的 reproducibility 。
OpenAI 是这么说的:... If specified, our system will make a *best effort* to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is *not guaranteed*
Anthroic 是这么说的:...Note that even with temperature of 0.0, the results will not be fully deterministic.