Danyang Liu

> For future anyone has the empty model weight issue. I solved it by referring this issue: [microsoft/DeepSpeed#4720](https://github.com/microsoft/DeepSpeed/issues/4720). But the simple suggestion is using deepspeed zero2, cause only zero3 has...

> Thank you for your prompt reply ! Somehow I got the kind of selected_index > embedding length error because llama embedding shape is 32002, but otter pad_idx is 32003....

> Thanks for sharing. I am now training Otter to treat multiple pictures as videos. Since the number of pictures is of variable length, batchsize=1 is currently used for processing....

> Thank you for your interest. > > Accomplishing a multi-image response with a single instruction can be easily done by adhering to the dataset format found here: > >...