← Back to context Comment by marcalc 10 months ago What do you mean by draft model? And how would one disable it? Cheers 1 comment marcalc Reply _neil 10 months ago A draft model is something that you would explicitly enable. It uses a smaller model to speculatively generate next tokens, in theory speeding up generation.Here’s the LM Studio docs on it: https://lmstudio.ai/docs/app/advanced/speculative-decoding
_neil 10 months ago A draft model is something that you would explicitly enable. It uses a smaller model to speculatively generate next tokens, in theory speeding up generation.Here’s the LM Studio docs on it: https://lmstudio.ai/docs/app/advanced/speculative-decoding
A draft model is something that you would explicitly enable. It uses a smaller model to speculatively generate next tokens, in theory speeding up generation.
Here’s the LM Studio docs on it: https://lmstudio.ai/docs/app/advanced/speculative-decoding