Monami Banerjee comments

Repositories
Issues
Comments

Results 12 comments of


                                            Monami Banerjee

DPO training error `RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!`

Current command and error: **Command:** ``` NPROC_PER_NODE=8 \ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \ swift rlhf \ --rlhf_type dpo \ --model_type llava-onevision-qwen2-0_5b-ov \ --beta 0.1 \ --rpo_alpha 0.1 \ --sft_type lora \ --dataset rlaif-v#1000...

Cannot run inference with Cambrian-1-34B on multi-GPU

The whole stack: ``` 2024-07-20 16:49:05 PID=2363969 __init__.py:49 setup_logging() INFO → 'standard' logger initialized. 2024-07-20 16:49:06 PID=2363969 builder.py:119 load_pretrained_model() INFO → Loading Cambrian from cambrian-34b 2024-07-20 16:49:06 PID=2363969 builder.py:105 build_vision_tower_aux_list()...