News for hackers. Stuff that matters.

A comment on Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models. Parent comment

Re:Inference-Aware Fine-Tuning for Best-of-N Sampling in Lar... by codelion on Monday April 28, 2025 @01:42AM (#43817979)
Not standard but one of several techniques, you can see them in our open source inference proxy - https://github.com/codelion/optillm

Cerebras has used optillm for optimising inference with techniques like CePO and LongCePO.

[ Parent | on HN ]

There are no comments on this comment yet.