Yao Li

icon indicating a website link https://cs.adelaide.edu.au/~yaoli/ icon indicating an email [email protected]

icon company Microsoft icon location Seattle, WA 98109 icon location Senior Applied Scientist at Microsoft

Results 3 comments of Yao Li

6G GPU memory,batch_size=1 with D1 network,still got CUDA out of memory

I got the same problem on my Titan rtx

size mismatch error

I have reproduced the error in the "colab-demo-for-donut-base-finetuned-docvqa.ipynb" too. [/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py](https://localhost:8080/#) in _load_pretrained_model(cls, model, state_dict, loaded_keys, resolved_archive_file, pretrained_model_name_or_path, ignore_mismatched_sizes, sharded_metadata, _fast_init, low_cpu_mem_usage, device_map, offload_folder, offload_state_dict, dtype, is_quantized, keep_in_fp32_modules) 3530 "\n\tYou may...

size mismatch for encoder.model.layers.1.downsample.norm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).

the google colab demo has the same size mismatch issue too. I have reproduced the error in the "colab-demo-for-donut-base-finetuned-docvqa.ipynb" too. [/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py](https://localhost:8080/#) in _load_pretrained_model(cls, model, state_dict, loaded_keys, resolved_archive_file, pretrained_model_name_or_path, ignore_mismatched_sizes, sharded_metadata,...