←back to thread

Llama.cpp 30B runs with only 6GB of RAM now

(github.com)
1311 points msoad | 2 comments | 31 Mar 23 20:37 UTC | HN request time: 0.408s | source
1. kthakore ◴[01 Apr 23 01:48 UTC] No.35396216[source]▶
Where do you download the tokenizer.model that is needed to convert the GPT4ALL model to the appropriate format?
replies(1): >>35396497 #
2. Rzor ◴[01 Apr 23 02:40 UTC] No.35396497[source]▶
lesmo provides a magnet uri to all models here. it's inside (499kb): https://github.com/facebookresearch/llama/pull/73/files/016a...