tiny NNs distilled from LLMs can produce some amazing results, i'm surprised it'... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		electroglyph 8 months ago \| parent \| context \| favorite \| on: Tokasaurus: An LLM inference engine for high-throu... tiny NNs distilled from LLMs can produce some amazing results, i'm surprised it's not more common tbh

cpard 8 months ago [–]

I agree, there are impressive results. This just came out from Berkeley https://arxiv.org/abs/2506.04178

But still, I mainly see work on this direction in academia.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact