Temperature and Maximum Output Length in Foundation Model Inference

AWS Certified AI Practitioner · Applications of Foundation Models · By Super Admin

Temperature controls the randomness and creativity of foundation model outputs, while maximum output length controls how many tokens a model generates, and both must be tuned for the use case. Inference parameters are supplied as part of the input alongside the prompt, and they…

This article is for paid accounts

Read it in full in your study workspace
0.0 (0 ratings)

Discussion (0)

No discussion on this article yet — be the first to comment.

Please sign in to join the discussion.