alex shengzhi li

Thank you, Alexandra and David. I appreciate the prompt reply. A follow up question... the snorkel 0.9.1 does not contain a snorkel module. I am trying to run some notesbooks,...

Thank you so much for answer! @yvfengZhong

Curious about your work, has it been published?

Did anyone find a soltuion?

Can you please provide some example of your training data? system="""system\nAnswer the questions.""", roles=("user\n", "assistant\n"), I was wondering why you chose to add a new conversation format. I was trying...

Can anyone share the filtered_dataset json for the 34b training? Yours, Alex On Apr 24, 2024 at 4:42 AM -0700, Rohith Bojja ***@***.***>, wrote: > #!/bin/bash > deepspeed llava/train/train_mem.py >...

https://github.com/AttentionX/InstructBLIP_PEFT?tab=readme-ov-file It semms like the authors have no motivatioon to release the finetuning script, but here is a repo that claims to do the same

what would it take for the community to help?

Any support on this? We found out that the training is doing just next token prediction but I think most folks are doing instruction tuning

For sleep eeg to epilepsy, I also fix a basic model gradient kept accumulating bug. After that, my result on epilepsy are still bad with the default number of samples....