meta-llama / llama

Inference code for Llama models
Other
55.49k stars 9.47k forks source link

I want to use 65B on 4 A100-80G to talk like GPTChat. What should I do #192

Closed Chting closed 1 year ago

breadbrowser commented 1 year ago

No description provided.

I recommend using this. https://github.com/randaller/llama-chat

Chting commented 1 year ago

I recommend using this. https://github.com/randaller/llama-chat

Thank you for your answer. I have used this one. It does not support multiple GPUs at present

TensorCraft commented 1 year ago

Check this, Maybe helpful.

Chting commented 1 year ago

Check this, Maybe helpful.

Thank you, I have tried this

XuyaoWang commented 1 year ago

this link is another way to make llama looks like a ChatGPT

WuhanMonkey commented 1 year ago

Closing as we released Llama 2 chat.