Childish Zenith issues

Repositories
Issues
Comments

Results 2 issues of


                                            Childish Zenith

Clarification Needed: Why is topk=2 Set for Greedy Decoding?

Reference: https://github.com/thunlp/InfLLM/blob/main/inf_llm/chat.py#L168

Fail to reproduce the "Training-From-Scratch" performance

Thanks for your impressive work. I try to reproduce the "Training-From-Scratch" performance using: `bash tools/train_ego4d_twogpu.sh configs/ego4d_nlq_v2_internvideo_1e-4.yaml scratch_2gpu 0,1`. The evaluation result is about 14-15 R@1, IoU=0.3 on the validation set,...