Skip to content
This repository has been archived by the owner on Jun 18, 2024. It is now read-only.

Issues: google-research/albert

97 Open 85 Closed
97 Open 85 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Why do I find inconsistencies between the output of my ALBERT model converted to ONNX format and tested with ONNX Runtime, compared to the original PyTorch format model?
#277 opened Dec 22, 2023 by Orient12
Load in Browser Tensorflow
#276 opened Jul 2, 2023 by sysmaya
The results can't be reproduced
#269 opened Jul 29, 2022 by kavin525zhang
2
Difference between v1 and v2 for xxlarge
#266 opened Jun 12, 2022 by yanaiela
when training in Race , The eval_accuracy is flat , it only has three numbers which are 0.0, 0.33334, 0.66667, 1.0
#264 opened May 25, 2022 by AGuangzzz
How to get the test embeddings from output of fine-tuned model (tutorial)
#260 opened Mar 7, 2022 by kelseyneis
Default Tutorial Not Working - Can't download MRPC data
#257 opened Feb 6, 2022 by Jadiker
2
Probable error on line 306 in create_pretraining_data.py for albert
#256 opened Jan 18, 2022 by wjdghks950
which word segmentation tool is used for pretraining Chinese ALBERT
#250 opened Nov 7, 2021 by bojone
Discrepancy in tokenization results using albert's tokenizer and sentencepiece library
#249 opened Oct 18, 2021 by anjali-chadha
fine tune on my own English dataset
#248 opened Sep 11, 2021 by cxx-cindy
albert base fine-tuned on squad2.0 gets stuck in loop when predicting on new file
#243 opened Mar 29, 2021 by alexander-fichtl
1
The exact English pretraining data and Chinese pretraining data that are exact same to the BERT paper's pretraining data.
#242 opened Mar 23, 2021 by guotong1988
torch.nn.modules.module.ModuleAttributeError: 'AlbertEmbeddings' object has no attribute 'bias'
#241 opened Mar 17, 2021 by dhs29
1
The output of the features of a given text consists of two tensor. Are they both the deep features?
#240 opened Mar 17, 2021 by FriedaSmith
Where to download "all.txt" to train the sentencepiece?
#238 opened Dec 19, 2020 by YuHengKit
where to download the "spm_model_file" called "30k-clean.model"
#237 opened Dec 9, 2020 by Sarah-Callies
Could you provide the training hyper paras
#235 opened Nov 10, 2020 by juyiming
1
[Implementation] Sentence order prediction (SOP) label for a single-chunk-document in create_pretraining_data.py
#234 opened Oct 26, 2020 by joongbo
albert_base可以使用多块GPU同时训练么
#233 opened Oct 17, 2020 by Yaaasuo
ValueError: Expected input batch_size (864) to match target batch_size (32).
#232 opened Sep 30, 2020 by abhibha1807
[Problem/ Squad V2] the result is too low compare with the F1 score in paper, Is something wrong?
#230 opened Sep 22, 2020 by Gs-Zhang
7
Can ALBERT's parameter sharing concept be used in image-GPT paper implementation?
#229 opened Sep 17, 2020 by spygaurad
Finetune with multiple GPU
#228 opened Sep 11, 2020 by ReyonRen
Error creating and exporting TFLite after fine-tuning (using run_squad_v1.py/run_squad_v2.py)
#227 opened Aug 19, 2020 by manojpreveen
2
ProTip! no:milestone will show everything without a milestone.