zhang cheng

How to repeat the Near-optimal model-based planner and Planning experiments(in old dynamics))？

4

I am wondering how to use the deprecated MediumLevelPlanner to repeat. I met this problem

problem with creat_semi_dataset.py

1

Linux cheng 6.8.0-51-generic #52-Ubuntu SMP PREEMPT_DYNAMIC Thu Dec 5 13:09:44 UTC 2024 x86_64 x86_64 x86_64 GNU/Linux NVIDIA-SMI 550.120 Driver Version: 550.120 CUDA Version: 12.4 when I was using creat_semi_dataset.py this...

HI when I was training with vicuna v1.3, the loss is always nan, my training script is this `torchrun --nproc_per_node=1 medusa/train/train_legacy.py --model_name_or_path lmsys/vicuna-7b-v1.3 \ --data_path mistral.json \ --bf16 True \...

Hi Pathak, I am currently working on image inpainting algorothim and doing experiments on several datasets. Can you share the dataset through a private link in my email address. That...