How to run baby llama? - Githubissues

srush / llama2.rs

A fast llama2 decoder in pure Rust.

MIT License

995 stars 54 forks source link

How to run baby llama? #42

Open tairov opened 8 months ago

tairov commented 8 months ago

Hi. Thanks for this port. I was trying to inference the babyllama, but seems that this port doesn't support it anymore? Like the original llama2.c compatible stories*.bin model. How can I do this ?

srush commented 8 months ago

Currently it doesn't support that model, I'll add a way to run it.