-
**Describe**
Model I am using (UniLM, MiniLM, LayoutLM ...): **LayoutReader**
Hi @zlwang-cs
I am using `layoutreader` to predict layout-only data like this, which the order is from right to left,…
-
Hi - Am trying to debug a few issues I am facing here, upon detailed examination it seems that this part of the readme does not exist anymore, i.e. I cannot find the 'scripts' folder anywhere inside l…
-
**Describe the bug**
Model I am using (UniLM, MiniLM, LayoutLM ...):
The problem arises when using:
* [ ] the official example scripts: (give details below)
* [ ] my own modified scripts: (give …
-
currently i am working on TR-OCR
MODEL USED- VisionEncoderDecoderModel
code -
/**
from PIL import Image
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
processor = TrOCRPro…
-
**Describe the bug**
Model I am using (UniLM, MiniLM, LayoutLM ...):
The problem arises when using:
* [ ] the official example scripts: (give details below)
* [ ] my own modified scripts: (give …
-
### Model description
DeltaLM is a multilingual encoder-decoder architecture that regards the decoder as the task layer of off-the-shelf pre-trained encoders. This architecture introduces an interl…
-
Describe
Model I am using BeiT-3:
Hello, I found that BeiT-3 is pre-trained mainly on English data. I wish to pretrain BeiT3 on Chinese data. Will you release the pre-training code?
-
Hello,
I'm trying to run the evaluation of text detection using the provided pre-trained model of DiT in your source code. Unfortunately, I can't access the link you gave us in the `README.md` file…
-
**Different trained TrOCR models require custom arg changes in the script**
Model I am using TrOCR:
The problem arises when using:
* [x ] the official example scripts: (give details below)
Whe…
-
Hi,
I found that the model used in BIET-3 based on torchscale is not as what the paper described.
In the multiway transformer, the self-attention layer should be shared across different modality. …