-
I want to compare docvecs obtained from bert with XLnet. In case of bert I take average of last 4 layers to obtain docvec but the max seq is limited to 512 tokens. As I read in XLnet also the seq-len…
-
I am doing a classification problem. there are about 200 labels in total, and 20 000 examples.
When using the XLNet-Base model, I do a fine-tuning, do a 5 folder cross-validation and the results(…
-
Hello! I've found a performance issue in baselines/models/xlnet/data_utils.py: `dataset = dataset.batch(bsz_per_core, drop_remainder=True)`[(here)](https://github.com/CLUEbenchmark/CLUE/blob/5b1d19dc8…
-
https://yam.gift/2019/07/14/Paper/2019-07-14-XLNet-Paper/
Yam | AI | NLP | 人工智能 | 哲学 | 自然语言处理 | 机器学习
-
-
Hi, Thanks for your code, I replace the XLNet with BERT using the original hyper-parameter, get very very bad result. Did you ever try the BERT model instead of XLNet?
-
Hi, I am trying to only use xlnet model without the gcn for NER. I have ran train.py in the 'xlnet-ner' folder and obtained the saved weights - '4.pt' in a finetuning folder. However, I have issues wi…
-
Thanks for your work on xlnet extension! It is quite impressive with how quickly this has been done.
I have a question with importing xlnet package. When I tried running NER experiment, I got an erro…
-
I have pretrained XLNET model in Georgian lagnuage. Training has generated this files:
.…
Bagdu updated
5 years ago
-
### Description
Based on the training/eval script created in #806 , create unit/integration tests that ensures the stability of the API when setting the advanced hparams and also allowing to track i…