allenai/bilm-tf

Issues

• Pre-trained links do not work

  #245 opened 2 years ago by eduamf
  7

• Unable to train ELMO after loading all training files.

  #219 opened 5 years ago by Dragon615
  2

• 2021-10-29 14:13:30.313623: E C:\users\nwani\_bazel_nwani\mmtm6wb6\execroot\org_tensorflow\tensorflow\stream_executor\cuda\cuda_event.cc:49] Error polling for event status: failed to query event: CUDA_ERROR_OUT_OF_MEMORY

  #244 opened 3 years ago by justyyau
  0

• Preparing training data for a domain with many multi keyword token

  #240 opened 4 years ago by sathiyabalu89
  1

• Running into error on tests

  #241 opened 4 years ago by adideva98
  3

• How to use ELMo in Keras version?

  #227 opened 5 years ago by LucasJau
  1

• Saving the custom trained ELMO embedding (hdf5) in the format of tensorhub models

  #242 opened 4 years ago by sathiyabalu89
  0

• Perplexity per sentence implementation?

  #213 opened 5 years ago by BigBorg
  1

• Does any code about ELMO+ESIM?

  #237 opened 4 years ago by 14H034160212
  1

• Compute training time

  #239 opened 4 years ago by reobroqn
  0

• how to freeze some layers during training

  #231 opened 4 years ago by renukachittimalla
  1

• Exporting finetuned model to SavedModel format for Tensorflow Serving

  #238 opened 4 years ago by mohammedayub44
  6

• The PyTorch version replication of the "Deep contextualized word representations" is missing

  #236 opened 4 years ago by 14H034160212
  0

• elmo sentence embeddings using usage_token.py

  #235 opened 4 years ago by mchari
  0

• incremental training on less than 2000 sentences

  #234 opened 4 years ago by mchari
  2

• drastic impact of Changing the vocabulary on perplexity

  #233 opened 4 years ago by Krishnkant-Swarnkar
  1

• Import Error: No module named bilm.training when I try to incrementally train ELMo

  #232 opened 4 years ago by mchari
  1

• Training ELMO on TPU for generating embedding from custom dataset

  #230 opened 5 years ago by hazalturkmen
  0

• bug during data loading (and tests)

  #229 opened 5 years ago by tsteffek
  2

• why should vocabulary file be sorted in descending order by token count in our training data？

  #228 opened 5 years ago by showerage
  0

• UnicodeError when run example: python -m unittest discover tests/

  #225 opened 5 years ago by ruleGreen
  2

• [Question] Are there any plans to port this to Tensorflow 2?

  #221 opened 5 years ago by PhilipMay
  2

• Resume ELMo training after crash

  #217 opened 5 years ago by pjox
  1

• how many time it takes if I training a 5GB corpus on 1080ti

  #226 opened 5 years ago by SeekPoint
  0

• Out of range: Read fewer bytes than requested

  #224 opened 5 years ago by mohsen7394
  0

• How it works?

  #223 opened 5 years ago by ZXR-v2
  0

• [ Question ] When does the inner state of the LSTMs reset during training?

  #220 opened 5 years ago by tsteffek
  2

• it occur a error when read weights.h5py

  #218 opened 5 years ago by ttjjlw
  0

• Contributed german ELMo model

  #209 opened 5 years ago by PhilipMay
  7

• Contributed ELMo model for Basque

  #214 opened 5 years ago by stefan-it
  1

• How to dump_token_embeddings?

  #211 opened 5 years ago by yumath
  1

• Which tokenizer used for Japanese pretrained model?

  #210 opened 5 years ago by tringn
  2

• How could I use word-level ELMO easily?

  #212 opened 5 years ago by ricky9123
  3

• Shape of Embeddings?

  #216 opened 5 years ago by rachuang22
  0

• How to restart training of a model

  #215 opened 5 years ago by ashishjain1988
  2

• Problem Installing from Docker

  #208 opened 5 years ago by pvcastro
  0

• Checkpoint for Original (5.5B) version

  #207 opened 5 years ago by andreymalakhov
  0

• Give an option for the Checkpoint frequency

  #206 opened 5 years ago by aryankhandal0
  0

• fill each batch to exactly 20 tokens? 30tokens? 40tokens?

  #205 opened 5 years ago by MLjian
  0

• one sample maybe contain two sentences.

  #204 opened 5 years ago by MLjian
  0

• hub version elmo with colab tpu runtime produces eorror

  #203 opened 5 years ago by SharonLong328
  0

• Train Perplexity is very low but test is pretty high for Thai language

  #202 opened 5 years ago by SuphanutN
  0

• ResourceExhaustedError (see above for traceback): OOM when allocating tensor of shape [] and type float

  #195 opened 5 years ago by xiaoxiaoAurora
  1

• InvalidArgumentError while finetuning on new dataset

  #197 opened 5 years ago by ravikrn
  1

• How to fine tune

  #201 opened 5 years ago by pxk8001
  1

• Separate Training Files vs Single Training File

  #200 opened 5 years ago by agemagician
  1

• Any sample code for generating sentence embeddings using my trained model?

  #199 opened 5 years ago by masoudh175
  1

• Checkpoint files for medium elmo model

  #198 opened 5 years ago by abaheti95
  1

• [Question] Perplexity at the end of training

  #196 opened 6 years ago by mmarius
  2

• Will `dump_bilm_embeddings` change orders of inputs and outputs?

  #194 opened 6 years ago by yslin1995
  3