zhww
zhww
In the technical report,Object365 was used for pretrain, but I test mini-4B, it can't do object detection. So, what the detect data format or instructions are used during pretrain?
I do pretrain with zero3 will got errors, but lora fintune with zero3 is ok. The error info is: python3.10/site-packages/torch/distributed/distributed_c10d.py", line 3375, in reduce_scatter_tensor work = group._reduce_scatter_base(output, input, opts) torch.distributed.DistBackendError:...
能提供最新的https://huggingface.co/BAAI/BGE-VL-v1.5-mmeb这个模型在MMEB测试集的评估示例吗? 目前看评估代码还都是clip的模型,没有mllm相关的。