novarobot
/
llama-chat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
main
randaller 3 years ago committed by GitHub
parent a72dff1812
commit 78559d920c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File

6
README.md
Unescape Escape View File

@ -10,15 +10,15 @@ And on Shawn Presser's repo: https://github.com/shawwn/llama
[HF 🤗 version](https://github.com/randaller/llama-chat#hugging-face--version) by Yam Peleg and Jason Phang: https://github.com/ypeleg/llama & https://github.com/zphang [HF 🤗 version](https://github.com/randaller/llama-chat#hugging-face--version) by Yam Peleg and Jason Phang: https://github.com/ypeleg/llama & https://github.com/zphang
### Examples of chats here ## Examples of chats here
https://github.com/facebookresearch/llama/issues/162 https://github.com/facebookresearch/llama/issues/162
Share your best prompts, chats or generations here in this issue: https://github.com/randaller/llama-chat/issues/7 Share your best prompts, chats or generations here in this issue: https://github.com/randaller/llama-chat/issues/7
### System requirements ## System requirements
- Modern enough CPU - Modern enough CPU
- NVIDIA graphics card (2 Gb of VRAM is ok) - NVIDIA graphics card (2 Gb of VRAM is ok); HF version is able to run on CPU, or mixed CPU/GPU, or pure GPU
- 64 or better 128 Gb of RAM (192 would be perfect for 65B model) - 64 or better 128 Gb of RAM (192 would be perfect for 65B model)
One may run with 32 Gb of RAM, but inference will be slow (with the speed of your swap file reading) One may run with 32 Gb of RAM, but inference will be slow (with the speed of your swap file reading)

Write Preview
Loading…
Cancel
Save