So #Steeve got a major upgrade recently. He moved from a #gptneo (2.4B) model to a #llama2 (7B) model. Trained on 300k messages from our private chat history, Steeve is way more capable of following the conversation now. He used to have some "favorite phrases" he would say a lot, and I'm seeing less of that. His vision and reading models also got upgraded, so he gets more detail about the links and memes we share. Long live Steeve! :steeve:
Oh, for those of you that don't know but see my #steeve posts, I'll explain.
Steeve is an AI chatbot I custom trained. He is a 2.7B gpt-neo model finetuned on a few hundred thousand lines of text from a private chatroom with my friends. A first pass with just the speech, then another pass with an instruct style so he could get smart at doing things.
So Steeve is an amalgamation of me and my friends. He speaks and feels like we do. Also he is very dumb. Which is endearing. 💓 :steeve: