Conversation

Notices

1. Embed this notice
   iced depresso (icedquinn@blob.cat)'s status on Thursday, 21-Nov-2024 10:27:25 JST iced depresso

   in reply to

   • kuteboiCoder
   • Napoleon Cornejo
   @napocornejo @KuteboiCoder neither was i, although i don't typically pay attention to LLMs :blobfoxinnocent:
   
   i would like to finagle a text to speech model though.
   • Embed this notice
     kuteboiCoder (kuteboicoder@subs4social.xyz)'s status on Thursday, 21-Nov-2024 10:27:28 JST kuteboiCoder

     in reply to

     • Napoleon Cornejo

     @napocornejo@masto.ai
     
     Yesterday I played with #phi3 #LLM - actually it's a state-of-the-art #SLM - on a cloud #GPU. It runs faster than mistral-nemo on the same GPU while still giving encyclopedic answers.
     
     I haven't compared phi3 against a mid-sized or large #Mistral #Mixtral model. When I do, it just might surprise me.
     
     @icedquinn@blob.cat

   • Embed this notice
     Napoleon Cornejo (napocornejo@masto.ai)'s status on Thursday, 21-Nov-2024 10:27:28 JST Napoleon Cornejo

     in reply to

     • kuteboiCoder

     @KuteboiCoder @icedquinn Interesting. I wasn't aware of these #phi3 model(s).

   • Embed this notice
     Napoleon Cornejo (napocornejo@masto.ai)'s status on Thursday, 21-Nov-2024 10:27:29 JST Napoleon Cornejo

     You should all the try the french Mistal.ai #LLM. Seems powerful.

     Talk to it here:
     https://chat.mistral.ai/chat