issues
search
microsoft
/
DeBERTa
The implementation of DeBERTa
MIT License
1.97k
stars
224
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
RTD is not registed
#154
Eric-Chen-007
closed
3 weeks ago
1
Pretraining the deberta-v3 by larger context length.
#153
sherlcok314159
opened
2 months ago
2
Generator weights
#152
ir2718
opened
5 months ago
0
Fine-tune DeBERTa v3 language model, worthwhile endeavour?
#151
shensmobile
opened
7 months ago
5
How can I evaluate COPA dataset?
#150
KwanghyeonLee
opened
8 months ago
0
Reason for missing values in table for the Roberta-base, mrpc entry
#149
Aradhye2002
opened
9 months ago
0
No assert: Training does not start when using different tokenizer/ tokenized-data
#148
adriwitek
opened
9 months ago
0
Inference gives different results when using multiple gpus (distributed mode) vs just one gpu (not distributed mode)
#147
ThuongTNguyen
opened
9 months ago
0
Model is not initialized correctly when path to a pretrained model is provided via `pre_trained`
#146
ThuongTNguyen
opened
9 months ago
0
Question regarding symmetric KL Loss
#145
skbaur
opened
10 months ago
0
sklearn changed to scikit-learn to avoid pip install failure
#144
RajkumarGalaxy
opened
1 year ago
0
Fix typo
#143
mrm8488
opened
1 year ago
0
fix: Corrected code instructions in README.md
#142
zzc0430
opened
1 year ago
0
fix: sklearn -> scikit-learn
#141
zzc0430
opened
1 year ago
0
Trying to initialize model "large"
#140
Saivaks
opened
1 year ago
0
EOF error while running the rtd.sh script
#139
BartWesthoff
opened
1 year ago
1
change: reduce memory consumption
#138
YongWookHa
opened
1 year ago
2
Trying to run rtd_task.py on Windows
#137
Yuri-Albuquerque
opened
1 year ago
1
When calculating Qr, why is the W of content used instead of the W of position used?
#136
nebula303
opened
1 year ago
0
Eligibility for Commercial Use
#135
Hegelim
closed
1 year ago
1
Install fails due to use of deprecated `sklearn` package
#134
benfogelson
opened
1 year ago
0
Change from deprecated package name sklearn to correct scikit-learn
#133
benfogelson
opened
1 year ago
0
Load deberta-v3-large but got deberta-v2 model
#132
ChengsongLu
opened
1 year ago
2
Deberta-v3-base Generator model
#131
sharanyarc96
opened
1 year ago
2
n/a
#130
StephennFernandes
closed
1 year ago
0
AssertionError: RTD is not registed.
#129
StephennFernandes
closed
1 year ago
3
No module named 'torch._six'
#128
StephennFernandes
closed
1 year ago
2
Error when running the example code for pretraining the rtd model.
#127
soonilbae
opened
1 year ago
15
effectiveness of RTD
#126
martin-reczko
opened
1 year ago
0
Info on Deberta-v2-xlarge training infra
#125
karthickgopalswamy
opened
1 year ago
0
Microsoft
#124
omniteams
opened
1 year ago
0
mDeBERTa Generator model
#123
dadelani
closed
1 year ago
3
1. Add code for DeBERTaV3 pre-training; 2. Fix error in torch 1.11; 3…
#122
BigBird01
closed
1 year ago
0
Generator Model
#121
prajwal967
closed
1 year ago
1
Convert DeBERTa model to ONNX with mixed precision
#120
SergeyShk
opened
1 year ago
0
which version is torch ?
#119
XuJianzhi
closed
1 year ago
0
Fix: a few typos as I read through the README.md
#118
cpcdoy
closed
1 year ago
0
why vocab.txt and tokenizer.json not in pretrained model in huggingface ??
#117
XuJianzhi
opened
1 year ago
1
Code about deberta_v3
#116
BAOOOOOM
closed
1 year ago
1
AssertionError: [] in google coab
#115
yupesh
opened
1 year ago
0
Can you upload the code finetuned in SQuad 2.0? Thank you very much.
#114
junzai0215
opened
2 years ago
0
mDeBERTa large
#113
djstrong
opened
2 years ago
0
Can you tell me which token represents the overall representation of the sentence in the task of feature-extraction? The first token or the last token?
#112
junzai0215
opened
2 years ago
0
Where is the Gradient-Disentangled Embedding Sharing(GDES) part in the code?
#111
Cakeyan
closed
1 year ago
3
Can't run bash commands in /DeBERTa/experiments/glue/
#110
heya5
closed
2 years ago
0
out of memory
#109
Amazing-J
opened
2 years ago
18
How to pretrain DeBERTa v3 ??
#108
BinhMinhs10
closed
1 year ago
2
Why does the size of DeBERTaV3 double on disk after finetuning?
#106
nadahlberg
closed
2 years ago
2
where is ENHANCED MASK DECODER ACCOUNTS part in code?
#105
tjshu
closed
2 years ago
1
Evaluation hangs for distributed MLM task
#104
dannyel2511
opened
2 years ago
7
Next