New Phi-3.5 model is here
#3
by
virtualspectre
- opened
@virtualspectre have you tested the Phi-3.5 model for RAG, I hear its pretty good as is.
Nope, Just tested it, it is nowhere near the accuracy of your aligned model.
Nope, Just tested it, it is nowhere near the accuracy of your aligned model.
I did some research, and I hear it has some problems with refusals from my inner circle, do you know if there is a good base model I could start with that might not have refusals? I am looking to train another model but havent been able to pick the next parameter count and what people actually want from a model.. Thank you for any feedback I really appreciate you. I am gonna finish this 8B model and quantize it down then my work station will be free.