srush / llama2.rs

A fast llama2 decoder in pure Rust.
MIT License
995 stars 54 forks source link

readme commands doesn't work #6

Closed AsureDay closed 11 months ago

AsureDay commented 11 months ago

pip install torch transformers [auto-gptq](https://github.com/PanQiWei/AutoGPTQ) python export.py llama2-70b-q.bin

pip install torch transformers auto-gptq python export.py llama2-70b-q.bin

srush commented 11 months ago

Fixed! We're you able to get it to run?