I have temporarily paused my weekly news reports to pause for a moment and take stock to better gauge the content you all care about (and want to see more of in this community).
What sort of topics or areas of content would you like for me to cover every week or so?
I won’t guarantee I’ll be the best journalist in this regard, but I’d be more than happy writing or R&D’ing about any concept that was useful or interesting for one of your ideas or workflows.
I am still somewhat busy brainstorming standardized workflows to fine-tune and publish a fosai model to HuggingFace, but I’m all ears between now and then.
Let me know if there is something you’d like to see more of here at [email protected]!
EDIT: I am actively rewriting all [email protected] guides, so that’s one thing coming down the pipeline before the end of the month! Share more of your ideas or wish list items in the comments below.
Here are some ideas:
-
Comparisons/reviews of different AI models. (Example: llama2 is better than llama1 because x)
-
Tutorials for how to apply AI (Example: Making a song shuffling system with an llm and music metadata)
I’ve seen you doing a lot of stuff on here, so I also wanted to say: Don’t overwork yourself, and I appreciate the effort you already put in.
I appreciate this comment more than you will know. Thanks for sharing your thoughts.
It’s been a challenge realizing this time capsule is more than that - but a grassroots community and open-source project bigger than me. Adjusting the content to reflect shared interests has been a concept I have grappled with these last few weeks - especially as we exit some of the exciting innovations we saw earlier this year.
I think the type of content series you mention is the next step here - that being practical and pragmatic insights that illustrate / enable new workflows and applications.
That being said, this type of content creation will likely take more time than the journalistic reporting I’ve been doing - but I think it’s absolutely worth the effort and the next logical evolution of whatever this forum becomes.
Thanks again for your kind words. I work 5/6 day weeks in my tech job on top of this, so burnout is a real thing. I think I’ll go for a hike this week and reevaluate how to best proliferate and spread FOSAI.
If you’re reading this now and have ideas of your own - I’m all ears.
-
In general I would like posts about:
- Notable model releases, e.g. base models… Perhaps a weekly summary of all merges and fine-tunes that deserve a mention, but nowadays there are just too many to try them all, and few bring something new to the table.
- Major features being added to popular toolkits such as llama.cpp and exllama
- LLM papers explained for non-scientists :)
But then there’s the question, should there be regular posts about non-FOS stuff on /c/fosai? I’m not even sure exactly what the definition of a FOSAI model is… Mistral has a permissive license and the model is free to use, but if the training data and methods counts as the models “source”, isn’t it closed? AFAIK that stuff hasn’t been released.