Olicorne
Olicorne
Just linking #1315 here as I think it might be better to make it part of the first release that contains embeddings, otherwise we'll have to deal with the issue...
I hope you won't mind but I was wondering what were the blockers for this much awaited feature. What is the state of the code, what are questions left to...
I don't think that the lack of embedding model on most user's setup is an issue because ollama use is opt in. As long as you haven't set an embedding...
I was suddenly reminded of that prominent quote in the readme: > This app is under heavy development and it's far from stable. So my opinion is now that, as...
> We are using the same OpenAI api-key and base url for both inference and embedding. I think have separate config for each of them would be better, as it...
Related to #262 as there is no mechanism to tell the crawlers that they should update
It might be easier the other way around no? Afaik futo makes it easy to make specific layouts and can even import files Unexpected keyboard is so absolutely awesome i...
Alright. I also discovered that there is actually a url serving those stats directly, I think it would be nice to mention it at the top of that page.
> That's a good point, but they're not really changing much monthly either. We can just take out those graphs and have a line with the current count. I agree....
I'm also interested in your training setup. Especially because since you released Llama-Omni, meta released Llama 3.2 which includes Vision support. It would be great if we could adapt your...