BakLLaVA 1 can successfully see! And we're not even half way through our run 👀
The base model is a Mistral 7B, so this is possibly the first
@MistralAI
vision model! Model is hosted here and will be fully released soon:
BakLLaVA-1 is now available to everyone. We show Mistral-7B with vision outperforms Llama-2 13B on several tasks, but we've only scratched the surface. BakLLaVA-2 is cooking with a larger corpus and significant architectural improvements/innovations.
We are now ready to scale MoE with the objective of achieving GPT-4 performance thanks to our core team member
@Sentdex
and for
@togethercompute
for elevating us from GPU Poor to GPU Middle Class. Join our group and contribute to help accelerate OSS AI!
Special thanks to Together Compute for sponsoring Skunkworks with compute!
@togethercompute
This is just the beginning of many releases coming in the next weeks pushing the boundaries of OSS AI even further. Stay tuned for MoE updates!
@AdarrabYoussef
BakLLaVA-1's code is a fork of
adapted for Mistral-7B. Here's our repo (although some updates coming over the next day to clean up and incorporate some new features we added)