-
I run the program in pycharm, one error listed below occurs, how to solve it?
ValueError: Unrecognized model in weights/icon_caption_florence. Should have a `model_type` key in its config.json, or co…
-
# How the Transformers broke NLP leaderboards - Hacking semantics
With the huge Transformer-based models such as BERT, GPT-2, and XLNet, are we losing track of how the state-of-the-art performance is…
-
Hi, when I run run_classifier.py with use_bfloat16=True, I met the followint exception:
File "/home/wutlin/anaconda3/envs/py27/lib/python2.7/site-packages/tensorflow_estimator/python/estimator/es…
-
In an effort to use the feedback we receive to the fullest, we need to get a better handle on the feedback we've received thus far, and a plan to better manage future feedback.
We can explore more…
-
Congratulations to the authors on this excellent work.
I'd like to pretrain my own XLNet models. Then, I plan to do some NAS / design space exploration on models similar to XLNet.
My question is…
-
just as title
-
https://github.com/ThilinaRajapakse/simpletransformers/blob/ffc829f18532d6920de22ee1c55c84ee1ce796d8/simpletransformers/ner/ner_utils.py#L422
Refer to line 442:`cls_token_segment_id` define the segme…
-
**Is your feature request related to a problem? Please describe.**
It would be great if we can use other models like XLNet, T5 for classification/language generation
**Describe the solution you'…
-
Hello,
Thanks for the great tool. I'm excited to use ProtTrans for generating protein sequences, but I'm getting an index error in the example notebook (https://github.com/agemagician/ProtTrans/blo…
-
Hi,
I am trying to train XLNet on protein sequences. I am running into OOM error when running the script train.py using a TPUv3-8 with train_batch_size=128. (I also get OOM error with train batch siz…