vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Updating README after running 60B of llama.cpp

Browse source
This commit is contained in:
Joshua Herman 2023-03-13 09:43:34 -05:00 • committed by GitHub
parent 1808ee0500
commit bc2b35ec69
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -124,6 +124,8 @@ And here is another demo of running both LLaMA-7B and [whisper.cpp](https://gith
https://user-images.githubusercontent.com/1991296/224442907-7693d4be-acaa-4e01-8b4f-add84093ffff.mp4 https://user-images.githubusercontent.com/1991296/224442907-7693d4be-acaa-4e01-8b4f-add84093ffff.mp4
If you have a M1 Max you can run LLAMA 60B and it will use approximately 41GB of RAM.
## Usage ## Usage
Here are the step for the LLaMA-7B model: Here are the step for the LLaMA-7B model: