-
It seems Microsoft has been able to push the performance on STS-b to 92.5: https://github.com/microsoft/DeBERTa
Their models are available via huggingface, but I'm not sure if their STS fine-tuned …
-
https://yam.gift/2020/06/27/Paper/2020-06-27-DeBERTa/
Yam | AI | NLP | 人工智能 | 哲学 | 自然语言处理 | 机器学习
-
1. Additional metrics to test
* [high priority] BERTScore-sentence, MNLI, {RoBERTa, DeBERTA}, Entail - Contradict, top-k and top-p
* [medium] BERTScore-original, DeBERTa -- to see how much…
-
No such file or directory: 'log/confidence/rte_ent_deberta_base.json'
-
您好,大佬,我用97M的deberta_v2模型训练多分类模型,发现保存的模型400M,有点没搞明白啊
-
Hi, I want to report a issue that I found while running mlm.sh for deberta-base.
## Description
- Using mlm.sh script for distributed training with more than 1 nodes causes a hang.
- I have tracked…
-
Here's command and error message. Please advise and help fix it. Thanks!
sudo docker run -it --rm --gpus all -v $PWD:/project ghcr.io/els-rd/transformer-deploy:latest bash -c "cd /project && \
…
-
I have been trying to use the pretrained `DebertaV2ForMaskedLM` based on the [example code](https://huggingface.co/transformers/model_doc/deberta_v2.html), but it is not working. The following BERT co…
-
I am thinking about creating DeBERTa version of this project. Initially I thought to use it as a backbone, because it's easier to modify than llama.cpp, but performance is really important for my case…
-
Hi there,
I am trying to use DebertaV3 as an alternative to BERT for an experiment that requires `torch.func` transformations. However, since Deberta implementation relies on a [`torch.autograd.Fun…