google-research albert issues

google-research / albert

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

Apache License 2.0

3.22k stars 572 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Albert

#279 Albertjabal closed 4 months ago
0
Albet

#278 Albertjabal closed 4 months ago
0
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 Orient12 opened 6 months ago
0
Load in Browser Tensorflow

#276 sysmaya opened 1 year ago
0
Made README.md more Readable

#275 Aryanutkarsh opened 1 year ago
0
Replace deprecated `tf.contrib.data.map_and_batch(...)` with `tf.data.experimental.map_and_batch(...)`.

#274 copybara-service[bot] closed 1 year ago
0
Replace deprecated `tf.contrib.data.parallel_interleave(...)` with `tf.data.experimental.parallel_interleave(...)`.

#273 copybara-service[bot] closed 1 year ago
0
Bump tensorflow from 1.15.2 to 2.11.1

#272 dependabot[bot] opened 1 year ago
0
Bump tensorflow from 1.15.2 to 2.9.3

#271 dependabot[bot] closed 1 year ago
1
Improvement to how the `app` and `pages` files conflict is shown. Especially the last log line `"pages/" - "app/"` made it seem like you should remove the `pages` folder altogether. This was a bug in how the `''` case was displayed. After having a look at this I went further and added exactly which file caused the conflict given that `app` allows you to create `app/(home)/page.js` and such it saves some digging for what the actual conflicting file is. Similarly in `pages` both `pages/dashboard/index.js` and `pages/dashboard.js` are possible.

#270 albrtkinn closed 1 year ago
0
The results can't be reproduced

#269 kavin525zhang opened 1 year ago
2
tokenization: log spm usage only in debug mode to avoid console spamming

#268 stefan-it opened 2 years ago
0
Wrong evaluate result on Squad2.0

#267 YuxuanJiang1 closed 2 years ago
0
Difference between v1 and v2 for xxlarge

#266 yanaiela opened 2 years ago
0
Bump tensorflow from 1.15.2 to 2.7.2

#265 dependabot[bot] closed 1 year ago
1
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 AGuangzzz opened 2 years ago
0
Bump tensorflow from 1.15.2 to 2.6.4

#263 dependabot[bot] closed 2 years ago
1
Remove unused comments related to Python 2 compatibility.

#262 copybara-service[bot] closed 2 years ago
0
Explicitly import estimator from tensorflow as a separate import instead of

#261 copybara-service[bot] opened 2 years ago
0
How to get the test embeddings from output of fine-tuned model (tutorial)

#260 kelseyneis opened 2 years ago
0
Prediction Fails on default Colab

#259 Jadiker closed 3 months ago
2
Bump tensorflow from 1.15.2 to 2.5.3

#258 dependabot[bot] closed 2 years ago
1
Default Tutorial Not Working - Can't download MRPC data

#257 Jadiker opened 2 years ago
2
Probable error on line 306 in `create_pretraining_data.py` for albert

#256 wjdghks950 opened 2 years ago
0
Minor bug fix

#252 copybara-service[bot] closed 2 years ago
0
Internal Google change

#251 copybara-service[bot] closed 2 years ago
0
which word segmentation tool is used for pretraining Chinese ALBERT

#250 bojone opened 2 years ago
0
Discrepancy in tokenization results using albert's tokenizer and sentencepiece library

#249 anjali-chadha opened 2 years ago
0
fine tune on my own English dataset

#248 cxx-cindy opened 2 years ago
0
Wrong pieces for control symbols after loading SentencepieceProcessor from official model

#247 JanKaul closed 2 years ago
2
Bump tensorflow from 1.15.2 to 2.5.1

#246 dependabot[bot] closed 2 years ago
1
Bump tensorflow from 1.15.2 to 2.4.0

#245 dependabot[bot] closed 2 years ago
1
Add an "excluded_tvars" arg in the create_optimizer function, which can be used to forbid updating the selected variables.

#244 copybara-service[bot] closed 3 years ago
0
albert base fine-tuned on squad2.0 gets stuck in loop when predicting on new file

#243 alexander-fichtl opened 3 years ago
1
The exact English pretraining data and Chinese pretraining data that are exact same to the BERT paper's pretraining data.

#242 guotong1988 opened 3 years ago
0
torch.nn.modules.module.ModuleAttributeError: 'AlbertEmbeddings' object has no attribute 'bias'

#241 dhs29 opened 3 years ago
1
The output of the features of a given text consists of two tensor. Are they both the deep features?

#240 FriedaSmith opened 3 years ago
0
train albert on custom dataset

#239 mlcom closed 3 years ago
0
Where to download "all.txt" to train the sentencepiece?

#238 YuHengKit opened 3 years ago
0
where to download the "spm_model_file" called "30k-clean.model"

#237 Sarah-Callies opened 3 years ago
0
Bump tensorflow from 1.15.2 to 2.3.1

#236 dependabot[bot] closed 3 years ago
1
Could you provide the training hyper paras

#235 juyiming opened 3 years ago
1
[Implementation] Sentence order prediction (SOP) label for a single-chunk-document in create_pretraining_data.py

#234 joongbo opened 3 years ago
0
albert_base可以使用多块GPU同时训练么

#233 Yaaasuo opened 3 years ago
0
ValueError: Expected input batch_size (864) to match target batch_size (32).

#232 abhibha1807 opened 3 years ago
0
Bump tensorflow from 1.15.2 to 1.15.4

#231 dependabot[bot] closed 3 years ago
1
[Problem/ Squad V2] the result is too low compare with the F1 score in paper, Is something wrong?

#230 Gs-Zhang opened 3 years ago
7
Can ALBERT's parameter sharing concept be used in image-GPT paper implementation?

#229 spygaurad opened 3 years ago
0
Finetune with multiple GPU

#228 ReyonRen opened 3 years ago
0
Error creating and exporting TFLite after fine-tuning (using run_squad_v1.py/run_squad_v2.py)

#227 manojpreveen opened 3 years ago
2