MingxiaoLi

questions about the VLNCE dataset

13

Hi, I feel quite confused about the dataset. In the vlnce gt dataset, there is locations and actions sequence, however when I use the simulator there is "vlnce-oricle action" in...

can not conduct per-tensor quantisation?

4

Hi below is my config file: version: 1.0 model: name: bert framework: pytorch # Mandatory: possible values are pytorch and pytorch_fx. device: cpu quantization: approach: quant_aware_training # Mandatory: Quantization approach,...

Training for the best model

10

Hi, I am really interested in your work, and I have been trying to reproduce the results. Could you kindly inform me how many epochs did you train the best...

multi-text video generation

3

Thanks for the great work. I am wondering could this framework perform mulit-text long videl generation ? Thought the title of the slayer example is "multi-text conditioned long video generation",...