Comment

Comment by Der_Einzige

It's because all forms of sampler settings destroy safety/alignment. That's why top_p/top_k are still used and not tfs, min_p, top_n sigma, etc, why temperature is locked to 0-2 arbitrary range, etc

Open source is years ahead of these guys on samplers. It's why their models being so good is that much more impressive.

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton