-
https://github.com/huggingface/transformers/blob/a14d62b0b11e6cb0c64059606e4f8dbf78e40e41/src/transformers/pipelines/__init__.py#L311
Is this intentional? I noticed the default is an empty dict but…
-
欢迎您反馈PaddleNLP使用问题，非常感谢您对PaddleNLP的贡献！
在留下您的问题时，辛苦您同步提供如下信息：
- 版本、环境信息
1）PaddleNLP和PaddlePaddle版本：paddlenlp 2.2 paddlepaddle 2.2
2）系统环境：linux
- 复现信息：使用PaddleOCR ocr代码多卡训练ser任务即可
https://github.c…
-
I wanted to check if there are any plans to add support for OPT models to optimum?
-
Hello,
Thanks for the great work with the LayoutXLM.
I wonder if you could share some of your work with the dataset used for pretraining. I know this is not possible to share dataset itself, due t…
-
**Describe**
Model I am using is LayoutLMv2:
(Link of the demo for reference: https://huggingface.co/spaces/nielsr/LayoutLMv2-FUNSD )
I do get 'questions' & 'answers' as separate colored boxes …
-
I am trying to use [layoutxlm model](https://huggingface.co/microsoft/layoutxlm-base), but I get the following error when loading either the tokenizer or the model with respectively `AutoTokenizer.fro…
-
Hello,
I would like to continue the pre-training of the LayoutXLM on my own domain data, nevertheless I only found scripts to perform fine-tuning on particular tasks (funsd and xfun).
Is it possib…
-
Hi，I am trying to Reproduce Results of LayoutXLM on XFUND-zh(RE task).
But The result is quite different, my f1-score is 0.073(vs 0.707 as you posed).
I am wondering why this case happen, I did some…
-
**Describe**
Model I am using (UniLM, MiniLM, LayoutLM ...): LayoutXLM
I cannot find pretrained LayoutXLM **Relation Extraction** model for **FUNSD** dataset. It is only available for XFUN
-
When I am using LayoutXLM pretrained model to initialize a LayoutXLM-base model, It seems that the pretrained model's weights are not loaded correctly.
**Running code:**
from layoutlmft.models.lay…
zlj-7 updated
3 years ago