News for hackers. Stuff that matters.

A comment on Non-determinism in GPT-4 is caused by Sparse MoE. Parent comment

Re:Non-determinism in GPT-4 is caused by Sparse MoE by og_kalu on Saturday August 05, 2023 @08:13AM (#37011246)
Fine-tuned MedPalm is worse than GPT-4 on most Medical Challenge Tests. Fine-tuned Minerva is much worse on arithmetic benchmarks.

The LLM space is just different. There's no guarantee a fine-tuned model will beat a bigger generalist one.

[ Parent | on HN ]

There are no comments on this comment yet.