These models are huge. I assume they are not quantized down to 4bits yet. | Hacker News

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

bhouston on April 19, 2023 | parent | context | favorite | on: StableLM: A new open-source language model

These models are huge. I assume they are not quantized down to 4bits yet.

brucethemoose2 on April 19, 2023 [–]

Quantized versions will pop up on huggingface very soon, if they arent already there. It takes basically no time, much less than something like a alpaca finetune.

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