Recent searches
Search options
This is the Llava:34B LLLM (local large language model) running on my #MacBook Pro describing a #screenshot from #BBC News. This, to me, is as good info as #BeMyAI would provide using #GPT4, so it goes to show that we can do this on-device and have some really meaningful results. Screenshot attached, #AltText contains the description.
Lately, I've taken to using this to describe images instead of using GPT, even if it takes a little longer for results to come back. I consider this to be quite impressive.
@FreakyFwoof Wow, I wish my hardware was anywhere near that good. I'm lucky enough to run the 7 and 13B. And, this isn't even the *best* Llava 34B can do right now! Ollama will be updated so Llava can take in an even better quality screenshot than it already does!
@pixelate It's great. I'd say this is better than GPT 3.5 when it was big. It's only going to get better from here as you say, so if this impresses us, where will we be in 6 months?
@FreakyFwoof Right? Local models describing whole videos, I bet.
@FreakyFwoof Installed Ollama and VOllama by @chikim the other day inspired by you, and I'm impressed too!
@ignasicambra @chikim Good. I told you it was interesting.
@FreakyFwoof That is fantastic