Sunny Sanyal
Sunny Sanyal
For Vision and Language pretraining cc3m, mscoco, SBUcaptions and VG are very relevant datasets. I haven't been able to download SBU captions and VG. Here are my questions. 1) How...
Dear Authors, Very impressive work. For reproducibility purposes could you please share the teacher logits files for all the teachers shown in this paper?
What do you mean by arguments --step, --stepmode, --use-valid, -j and --base. Also please explain their functions in the formation of blocks of MSDNET ?
Dear Authors , Could you please make the VQA finetuning codebase available to us?
Dear Authors, there is a bug in the token type ids of the BERT tokenizer as it is adding an extra token which leads to a mismatch in dimensions between...
Hey Authors, Thank you for the repo @ylsung . Can you please explain a bit how you guys sent the question and paired answers to the model as each question...
Very cool work. I have curious how to reproduce the figure 5 assessment provided in this paper.
It seems all the eval for LLMs are done using 1 GPUs can you suggest ways to run distributed eval?
Generated token/sec and token/gpu/sec benchmarking for 160m model.