Couldn't agree more. That's exactly what I felt like when Quake III came out... "Why is the screen so busy? So much garbage to distract from the game".
Maybe I'm just old now, but damn I loved Q2.
Also, all of the mods were incredible. Hopefully they will work... I think I have my WOD paks around still.
I really enjoy Wizard Coder for coding tasks. I use this specifically at work for code review and unit test writing. I also just generally like the Wizard LM.
Outside of that, I'll say that I haven't had a great experience with llama-2 yet, no matter how hard I've tried 🤣
I want to train / fine-tune a model
I want to train, or more likely fine-tune, a model on about 20 years worth of email and text data that I've collected.
The goal would be to train it how to respond like me in simple cases.
It's there a particular base model I should start with?
I'm also interested in anyone's experience in doing this kind of thing themselves.
I used it and was not impressed... I found Wizard LM to be far superior.
Also, I agree with @wagesj45 up there about training other models... but how would they detect that you're training other models with it? I think one of the best things you can do with a large model is to train a small specialist model.
Getting in shape and having a regular exercise routine, for sure. All of the side effects from that are incredible... Stamina, confidence, clearer thinking. So great.
Got a link or anything?
I would continue supporting rif if it was just an app where I had to get my own API key to run.