Closed shipengai closed 7 months ago
另外,论文中,没有Mixed visual embeddings和Mixed model weights等方法的性能提升对比实验。有计划放出这块对比吗?
This repo show the effectiveness of Mixed model weights for LLM and MLLM finetune. https://github.com/Alpha-VLLM/WeMix-LLM
Comprehensive sblation studies of Mixed visual embeddings and Mixed model weights will be updated soon.
We are sorry that this writing error is found after the paper is made public on arXiv. To clarify the 4 curves:
The purpose of this experiment is to show the benefits of jointly training on a text-only dataset (RefinedWeb in this case) in addition to the image captioning dataset. The growth of the loss on RefinedWeb is meant to show the compromised text reasoning capability.
@shipengai Please check the ablation study of SPHINX.