alt Hacker NewsAfter Anthropic, Moonshot is another model provider who restricts tweaking of sampling parameters. I do like the idea of the vendor verifier, though.
After Anthropic, Moonshot is another model provider who restricts tweaking of sampling parameters. I do like the idea of the vendor verifier, though.
If the post training is done with specific sampling parameters it would make sense to only use the parameters it was trained with.