MagicSource
MagicSource
What if didn;t use convnext added vision encoder?
Will opensource the HPT Pro?
Will consider add support Baidu?
Hi, wanna ask ,does mantis used image separator between images sending to LLM? From i can tell, llava doesn't have it and the data used in Mantis doesn't provide a...
Will the interleaved data opensource?
Is the training proj only?
1.5阶段不是加入了中文ocr数据么,为什么识别中文依旧没有任何效果
LLaVa consistently ranks among the top open-source projects, setting a high standard. Why not extend this excellence by opening up to Chinese datasets?
Add siglip flashattention support? I noticed that the navit-flashatten-siglip version already added flash attention, would transformers add it support inside ?
Just like webpages does, check it, and then it wont prompt password again..