From 80f26a7016bbfec04fec39c9c5480b6f57925850 Mon Sep 17 00:00:00 2001 From: randaller Date: Sun, 19 Mar 2023 16:10:24 +0300 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index e920982..91e1e65 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ Share your best prompts, chats or generations here in this issue: https://github One may run with 32 Gb of RAM, but inference will be slow (with the speed of your swap file reading) -I am running this on a [12700k/128 Gb RAM/NVIDIA 3070ti 8Gb/fast huge nvme with 256 Gb swap for 65B model] and getting one token from 30B model in a few seconds. +I am running PyArrow version on a [12700k/128 Gb RAM/NVIDIA 3070ti 8Gb/fast huge nvme with 256 Gb swap for 65B model] and getting one token from 30B model in a few seconds. For example, **30B model uses around 70 Gb of RAM**. 7B model fits into 18 Gb. 13B model uses 48 Gb.