Models that are worth writing home about are;
EXAONE-3.5-7.8B-Instruct - It was excellent at taking podcast transcriptions and generating show notes and summaries.
Rocinante-12B-v2i - Fun for stories and D&D
Qwen2.5-Coder-14B-Instruct - Good for simple coding tasks
OpenThinker-7B - Good and fast reasoning
The Deepseek destills - Able to handle more complex task while still being fast
DeepHermes-3-Llama-3-8B - A really good vLLM
Medical-Llama3-v2 - Very interesting but be careful
Plus more but not Gemma.
(I think the science behind blue light being bad for us is still up for debate, but it's hard for me to ignore the amount of anecdata I've heard, including my own experience using flux and the like)
Would be interested in studies refuting this.
> Ebert named the film the tenth worst film of 2004 and subsequently put it on his "Most Hated" list.
I dunno, I enjoyed it. I'm a simple man.
Edit: Also worth noting that her father is Ron Howard so she probably didn't need the money.
I do exactly that.
The act of writing helps me solidify that information in my brain - I have to process it to commit it to words. Paper works better than a text file, but a text file has the advantage of being faster and searchable. Once I've taken notes, I rarely go back and look at them. (Conversely, if I don't take notes, I'll wish I had)
I definitely do not take notes to abandon the information. Information I don't see the value in, I browse the web while listening. Some of that still sticks with me anyways.