You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Do you have any thoughts on converting llama/alpaca/vicuna models with LSG? Or would this be more difficult. It looks like they use rotary positional embeddings (RoPE) instead of absolute positional embeddings
The text was updated successfully, but these errors were encountered:
HF team added the Llama model few days ago.
From what I see in this implementation it is likely possible to add the LSG attention to a Llama model. RoPE isn't a problem as you can apply it before computing the score matrix.
I need to investigate this, I'll let you know within the week if I can create a conversion script.
Do you have any thoughts on converting llama/alpaca/vicuna models with LSG? Or would this be more difficult. It looks like they use rotary positional embeddings (RoPE) instead of absolute positional embeddings
The text was updated successfully, but these errors were encountered: