Cradawx@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agoShareGPT4V - New multi-modal model, improves on LLaVAsharegpt4v.github.ioexternal-linkmessage-square17fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkShareGPT4V - New multi-modal model, improves on LLaVAsharegpt4v.github.ioCradawx@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agomessage-square17fedilink
minus-squareCradawx@alien.topOPBlinkfedilinkEnglisharrow-up1·10 months agoI converted and quantized this to work in llama.cpp https://huggingface.co/nakodanei/ShareGPT4V-7B_GGUF
minus-squaredurden111111@alien.topBlinkfedilinkEnglisharrow-up1·10 months agonice. From my tests it seems to be about the same as LLava v1.5 13B and Bakllava. I’m starting to suspect that the CLIP-Large model all of these multi-model LLMs are using is holding them back.
Hopefully we get GGUFs soon
I converted and quantized this to work in llama.cpp
https://huggingface.co/nakodanei/ShareGPT4V-7B_GGUF
nice. From my tests it seems to be about the same as LLava v1.5 13B and Bakllava. I’m starting to suspect that the CLIP-Large model all of these multi-model LLMs are using is holding them back.