Re:Alpaca- An Instruct Tuned Llama 7B. Responses on par with...
by ulnarkressty on Monday March 13, 2023 @04:08PM
(#35141752)
I'm excited to see what the OpenAssistant crowd does with these models, they seem to have gathered the dataset to finetune them.
Lots of people use these models as talk therapy. We really need 1) standalone options, 2) reproducible weights with crowd sourced datasets to reduce biases (or at least know who you're talking to).
Lots of people use these models as talk therapy. We really need 1) standalone options, 2) reproducible weights with crowd sourced datasets to reduce biases (or at least know who you're talking to).