Teresa

There are many types of losses. Considering the fact a run can ezly generate thousands of check points, a validation loss would be particularly useful when trying to determine a...

Local Models

2

Hi, any thoughts on galactica(opt pretrained on pubmed and wiki) and llama(no domain specific knowledge trained yet) and any plan to release pretrained domain specific models for local inference? Thanks

disable cache

7

Hi,  I am trying to see if llama embedding is dates aware. The sberts are obviously not, however llama chat is able to derive absolute dates...

Making use of the gpio ports

2

Hi, first of all thank you for the excellent work! I am wondering if the web server could provide API for writing gpio ports. Currently the stream mode will block...