Ethan Yanjia Li

This is a breaking change in 2.4.0 because `freeze` is a function now

Those unlabeled area is red in your example prediction. I checked your implementation, you have 19 output classes for Cityscape, but just do argmax to get the class. How do...

Missing MPII annotation from preprocessed JSON file

2

I checked the MPII JSON annotations you posted in Google Drive, however, i found there're many annotations are missing from original MPII matlab version. Here're some examples: original MPII annotations:...

What is the 74_09_i2rnetv3_half_id/model_best.pth.tar used in the training

1

Is it some checkpoint from other datasets? thanks! https://github.com/zhoudaquan/rethinking_bottleneck_design/blob/master/mobilenext/mnext_mbv2.sh#L9

Any plan to re-implement the reward model training from InstructGPT?

2

Looks like the reward model is RankGen at the moment? But I thought we are going to have InstructGPT like K pair-wise ranking loss instead of this prefix/suffix one. Is...

Both web UI and CLI inference are working @DachengLi1 

Evaluation on untruthful, harmful, toxic or sensitive questions

5

Hi Vicuna team, Thanks for the great work to push the LLM fine-tuning a step further. this is especially amazing as a student/research led initiative. I found most of the...