Niall Taylor
Niall Taylor
Thank you for all the replies - I will let you know if my results improve. If they do not - it may be FARM is doing more under the...
Thanks for the reply. Very helpful, and looking forward to what is to come.
Actually, one quick question. To perform the SFT for MentalLLaMA, with the instruction training data for say, the DR task. Do you treat this as a standard auto-regressive objective and...
Thought so, was just double checking. Thanks for prompt reply! I'll keep you posted if I develop anything that could be brought into this repo.
Any updates on this?
Hello, thanks for the reply. In all honesty, I stumbled upon this after failing to find the implementation from the authors of the paper - it appears the github they...
That is very helpful - and kind of what I have found in my playing around in this space. I guess the CARP approach, or any prompt based approach is...
Awesome - thanks
I would also be interested in seeing these training scripts - would be very useful for extending this work