EricFillion/happy-transformer

Issues

• Unable to move to a different device

  #341 opened 3 months ago by brianangulo
  0

• Is there an option to run on gpu?

  #339 opened 10 months ago by Alaadel
  0

• FutureWarning: `resume_download` is deprecated

  #338 opened 10 months ago by Alaadel
  0

• TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]

  #323 opened 2 years ago by adeljebali
  1

• Memory exhausting

  #333 opened 2 years ago by MrSplinterRat
  0

• Does this support FP 16? and what is the VRAM requirement for training llama

  #332 opened 2 years ago by atorsvn
  0

• Large Dataset Fills up RAM (Enable "streaming" parameter to load_dataset)

  #331 opened 2 years ago by ddemillard
  0

• Too much time to eval&train

  #277 opened 2 years ago by saloyiana
  2

• Error while fine tuning GPT-J

  #287 opened 2 years ago by sallumandya1995
  1

• M1 GPU accell support

  #294 opened 2 years ago by ThatStella7922
  3

• Saving checkpoints

  #306 opened 2 years ago by dennymarcels
  2

• How do I save the model the huggingface?

  #318 opened 2 years ago by Rhitabrat
  1

• Get the loss per epoch instead of only 500 and 1000 epochs

  #319 opened 2 years ago by JVincentG
  4

• Suggestion: it may better have trust_remote_code parameter in HappyTransformer class

  #320 opened 2 years ago by lissa2077
  1

• Tries to use GPU (MPS) on Mac M1 and fails b/c model seems not loaded to device

  #326 opened 2 years ago by ephe-meral
  3

• I created a train.csv and I get an error about

  #307 opened 2 years ago by thistleknot
  5

• ValueError: Unrecognized configuration class <class 'transformers.models.t5.configuration_t5.T5Config'>

  #317 opened 2 years ago by Rhitabrat
  1

• Fine-tuning TextToText (T5) model on multiple tasks

  #313 opened 2 years ago by muzamil47
  1

• Are other languages compatible

  #325 opened 2 years ago by avakado0
  2

• Unable to fine-tune Question answer model

  #324 opened 2 years ago by mdnihal29
  0

• TypeError: TextEncodeInput must be Union[TextInputSequence, Tuple[InputSequence, InputSequence]]

  #303 opened 2 years ago by tuanndhust
  1

• [Feature suggestion] Parameter-Efficient Fine-Tuning

  #316 opened 2 years ago by almugabo
  0

• instruction fine tuning (for text generation)

  #312 opened 2 years ago by almugabo
  2

• Can i use t5 model to fine tune on text-to-code generation?

  #315 opened 2 years ago by mdnihal29
  1

• How to get multiple labels as output and not just one using classify_text ?

  #314 opened 2 years ago by mdnihal29
  2

• can we use a list of sentences inside generate_text, it seems to accept only string?

  #309 opened 2 years ago by syogeeshwari
  1

• startoftext, pad, and endoftext tokens

  #310 opened 2 years ago by thistleknot
  3

• wanted to use GLUE score or perplexity in the model evaluation.

  #308 opened 2 years ago by syogeeshwari
  2

• Feature Request Open AI Clip

  #305 opened 2 years ago by aamir-gmail
  1

• How to accelerate fine tune model with TPU using happy transformer?

  #304 opened 2 years ago by imrankh46
  3

• HI, sorry but your grammar model is very weak on real cases

  #293 opened 2 years ago by caprone
  5

• Model evaluation

  #302 opened 2 years ago by muzamil47
  5

• Sharing models to HuggingFace Hub

  #301 opened 2 years ago by kwen1510
  2

• circular import issue when importing with `transformers` and `happytransformer`

  #298 opened 3 years ago by maifeeulasad
  3

• GPT-Neo fine-tuning does not insert new lines in the output results

  #283 opened 3 years ago by MattJeanes
  3

• [FEATURE REQUEST] add support for the Conversational pipeline

  #296 opened 3 years ago by AbdelrhmanNile
  0

• OSError: Unable to load weights from pytorch checkpoint file for 'SentiApp/models/DISTILBERT_sentence/' at 'SentiApp/models/DISTILBERT_sentence/pytorch_model.bin'If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

  #255 opened 3 years ago by Y4rd13
  1

• Miscapitalization in Documentation

  #284 opened 3 years ago by ted537
  0

• The state dictionary of the model you are training to load is corrupted. Are you sure it was properly saved?

  #261 opened 3 years ago by kenanEkici
  3

• HappyTextToText hunging and fails

  #276 opened 3 years ago by socaseinpoint
  1

• Multi-GPU version

  #289 opened 3 years ago by Sukii
  3

• update the trainer.py to support encoding

  #253 opened 3 years ago by olwethumlimi
  2

• Running HappyGeneration with "gpt2-xl"

  #279 opened 3 years ago by siflueckiger
  1

• Enabling FP16 doesn't show loss--only steps.

  #285 opened 3 years ago by swcrazyfan
  0

• Saving option after epoch?

  #278 opened 3 years ago by AmoArt
  1

• Support for GTPJ-6B

  #262 opened 3 years ago by aamir-gmail
  6

• Training gpt with line by line

  #275 opened 3 years ago by zaharPonimash
  2

• Train in half precission

  #257 opened 3 years ago by hvico
  2

• Missing argument

  #270 opened 3 years ago by YovaKem
  1

• ImportError: cannot import name 'Speech2TextTokenizer' from 'transformers.models.speech_to_text' (/usr/local/lib/python3.7/dist-packages/transformers/models/speech_to_text/__init__.py)

  #256 opened 4 years ago by Y4rd13
  3