this post was submitted on 30 Nov 2023
1 points (100.0% liked)
LocalLLaMA
11 readers
4 users here now
Community to discuss about Llama, the family of large language models created by Meta AI.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
This is a fine-tune of Goliath-120B.
Didn't the author hypothesize that Goliath's interleaving of rows would degrade inference quality until it had been fine-tuned?
It will be interesting to see if this fine-tune supports that hypothesis.
Waiting for GUFF.