Could there be 8b, 7b and 1.5b version
I hope perlexity can release smaller models, so I could run on local.
That’s going to be super helpful too.
id second that, for us serfs who have limited resources on prem. ( 14 too, that is my 'sweet spot' )
You can check out our similar 8b model here, https://huggingface.co/BlueBeck/LlamaAligned-DeepSeekR1-Distill-8b , it simply aims to retain the reasoning ability of the 8b distil R1 model and to align with Llama 3.3, for better or for worse, rather than making any particular political statement.
They never intended to release a new model; they just want to annoy China and get a U.S. green card.
They never intended to release a new model; they just want to annoy China and get a U.S. green card.
They should want a China green card or it will break your fragile heart 😂