-
Hi there, thanks for maintaining this great model :)
I have not had any issues running the model using the default `--model_name_or_path bert-base-uncased` option in `train.sh`. However, I receieve…
-
你好，请问中英文数据集的处理方式是一样的吗？在代码中哪里有所体现
-
你好，由于实验室设备有限，如果可以使用cu训练的话，需要改哪些地方。
只用cpu来跑通与调试程序，
-
We need to do the training-dev split before wrapping the data in an `ABSA_Dataset` object that randomly picks a question template each time an instance is accessed. The dev set should then use all tem…
-
-
**Description**
I am trying to load tensorflow model in tritonserver. I am getting NormalizeUTF8. I am able to load this model in tensorserve 2.4 version. There I have installed tensorflow_text. I do…
-
Hi,
thanks for your great work!
Do you happen to know, where one can download both required `.jar` files?
I'm unable to download them from the official pages, making it impossible to evaluate m…
janpf updated
3 years ago
-
Hi, I am unable to train the CG-BERT model for any dataset. Below is the running command I've used and the result log. I have changed just the training batch size and evaluation interval. This error o…
-
https://github.com/songyouwei/ABSA-PyTorch/blob/9acab7e62e8aa52a8eb0b4a560d39740bc0f3798/models/asgcn.py#L12-L33
This part of code is commented with `Simple GCN layer, similar to https://arxiv.org/ab…
-
Hi,
I'm rerunning the code BERT-E2E-ABSA from https://github.com/lixin4ever/BERT-E2E-ABSA, which is based on transformers 2.0.0
I installed the latest transformers 3.0.2 (both from pip and souce…