Mei Li

Google SF

Results 4 comments of


                                            Mei Li

trafficstars

pyllama/downloads returns empty folders

> same on ubuntu, I can only get the token but not the model I am using ubuntu and it works well for me though.

Struggle with training LLaMA with a single GPU using both PT v1 and v2

Guess your torch version is too old?

Running web_server.py on Multi GPU instance.

Thanks for the tip @Maxpa1n It helped me a lot!

quantify llama 7B, the md5 value and the model size does not equals to the value in README

There must be something wrong on your side. 8bit quantization gives me decent result. Can you show your prompt and result?