google-research/albert

Issues

• Prediction Fails on default Colab

  #259 opened 8 months ago by Jadiker
  2

• Albert

  #279 opened 9 months ago by Albertjabal
  0

• Albet

  #278 opened 9 months ago by Albertjabal
  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 opened a year ago by Orient12
  0

• how to do inference for SQuAD style QA task using ALBERT?

  #212 opened 5 years ago by clrajapaksha
  2

• Load in Browser Tensorflow

  #276 opened a year ago by sysmaya
  0

• torch.nn.modules.module.ModuleAttributeError: 'AlbertEmbeddings' object has no attribute 'bias'

  #241 opened 4 years ago by dhs29
  1

• albert base fine-tuned on squad2.0 gets stuck in loop when predicting on new file

  #243 opened 4 years ago by alexander-fichtl
  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 opened 2 years ago by albrtkinn
  0

• The results can't be reproduced

  #269 opened 2 years ago by kavin525zhang
  2

• [Problem/ Squad V2] the result is too low compare with the F1 score in paper, Is something wrong?

  #230 opened 4 years ago by Gs-Zhang
  7

• Wrong evaluate result on Squad2.0

  #267 opened 2 years ago by YuxuanJiang1
  0

• Difference between v1 and v2 for xxlarge

  #266 opened 2 years ago by yanaiela
  0

• 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 3 years ago by AGuangzzz
  0

• How to get the test embeddings from output of fine-tuned model (tutorial)

  #260 opened 3 years ago by kelseyneis
  0

• Default Tutorial Not Working - Can't download MRPC data

  #257 opened 3 years ago by Jadiker
  2

• Probable error on line 306 in `create_pretraining_data.py` for albert

  #256 opened 3 years ago by wjdghks950
  0

• which word segmentation tool is used for pretraining Chinese ALBERT

  #250 opened 3 years ago by bojone
  0

• Discrepancy in tokenization results using albert's tokenizer and sentencepiece library

  #249 opened 3 years ago by anjali-chadha
  0

• Wrong pieces for control symbols after loading SentencepieceProcessor from official model

  #247 opened 3 years ago by JanKaul
  2

• fine_tune albert with run_classifier.py on GPU but the GPU-util is 0,why and how?

  #211 opened 5 years ago by yuanjun1991
  2

• fine tune on my own English dataset

  #248 opened 3 years ago by cxx-cindy
  0

• Could you provide the training hyper paras

  #235 opened 4 years ago by juyiming
  1

• TypeError: '<' not supported between instances of 'int' and 'NoneType' while only predicting, try to fix it, but not sure is it make sense

  #221 opened 4 years ago by alznn
  2

• Error creating and exporting TFLite after fine-tuning (using run_squad_v1.py/run_squad_v2.py)

  #227 opened 4 years ago by manojpreveen
  2

• The exact English pretraining data and Chinese pretraining data that are exact same to the BERT paper's pretraining data.

  #242 opened 4 years ago by guotong1988
  0

• The output of the features of a given text consists of two tensor. Are they both the deep features?

  #240 opened 4 years ago by FriedaSmith
  0

• train albert on custom dataset

  #239 opened 4 years ago by mlcom
  0

• Where to download "all.txt" to train the sentencepiece?

  #238 opened 4 years ago by YuHengKit
  0

• where to download the "spm_model_file" called "30k-clean.model"

  #237 opened 4 years ago by Sarah-Callies
  0

• [Implementation] Sentence order prediction (SOP) label for a single-chunk-document in create_pretraining_data.py

  #234 opened 4 years ago by joongbo
  0

• albert_base可以使用多块GPU同时训练么

  #233 opened 4 years ago by Yaaasuo
  0

• ValueError: Expected input batch_size (864) to match target batch_size (32).

  #232 opened 4 years ago by abhibha1807
  0

• How to prepare for the environment/data for fine-tuning?

  #216 opened 4 years ago by 517030910405
  2

• Can ALBERT's parameter sharing concept be used in image-GPT paper implementation?

  #229 opened 4 years ago by spygaurad
  0

• Finetune with multiple GPU

  #228 opened 4 years ago by ReyonRen
  0

• is it support fine tuning with tf2.x?

  #226 opened 4 years ago by ares5221
  1

• Albert-base-v2 training data

  #225 opened 4 years ago by slvcsl
  0

• why running run_squad_v2.py in prediction mode with dev-v2.0.json gets zero neg example

  #220 opened 4 years ago by urextra
  1

• tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed.

  #224 opened 4 years ago by YuHengKit
  0

• Is it possible to load pretrained model's checkpoint and pretrain other corpus with that checkpoint?

  #218 opened 4 years ago by sikaleo
  0

• invalid load key, '\x12'

  #217 opened 4 years ago by liu-x-p
  1

• use custom vocab.txt

  #214 opened 4 years ago by 2696120622
  1

• is inner_group_num exactly equal to num_hidden_layers/num_hidden_groups?

  #213 opened 5 years ago by lsy641
  0

• Where is the function of Factorized Embedding Parameterization?

  #210 opened 5 years ago by hntee
  2

• model isn't learning

  #207 opened 5 years ago by raviolli
  1

• Description problem of attention_mask.

  #208 opened 5 years ago by liushaoweihua
  0

• different parameter position with api doc

  #206 opened 5 years ago by cyjj
  0

• get Matthew_corr = 0 in eval on CoLA

  #205 opened 5 years ago by cyjj
  0

• Extremely large RAM consumption by create_pretraining.py

  #204 opened 5 years ago by sultanovazamat
  3