I never thought people would be upscaling models by increasing quantization prec... | Hacker News

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

		Taek on Jan 31, 2024 \| parent \| context \| favorite \| on: Mistral CEO confirms 'leak' of new open source AI ... I never thought people would be upscaling models by increasing quantization precision. The rationale makes sense bit its also a goofy outcome.

nullc on Feb 1, 2024 [–]

You should be able to upscale and fine tune to recover performance, I suppose!

Clearly we should train a diffusion model to denoise the weights of LLM transformer models. Yo dawg.

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