getalp/Flaubert

Issues

• AttributeError: module 'apex' has no attribute 'amp'

  #13 opened 5 years ago by keloemma
  4

• Example de paraphrase

  #44 opened 2 years ago by ExtReMLapin
  1

• From pytorch model (with hugging_face library) to XLM model

  #42 opened 3 years ago by ArthurVanSchendel
  1

• Continued training of FlauBERT (with --reload_model) -- Question about vocab size

  #40 opened 3 years ago by mcriggs
  1

• D'euro j'dis là du son dis bdia d dis fin dis djaifbfl j'dis. L'as bais. Eiabduua bsujsvd

  #43 opened 3 years ago by Kouakouhermann67
  1

• Import error in extract_split_cls.py - No module name tools

  #41 opened 3 years ago by ArthurVanSchendel
  1

• Will lemmatization negatively affect FlauBERT word embeddings?

  #38 opened 3 years ago by mcriggs
  9

• Pre-training FlauBERT with Google Colab?

  #39 opened 3 years ago by mcriggs
  1

• Extracting word embeddings from FlauBERT

  #37 opened 3 years ago by mcriggs
  1

• Different Categories for CLS dataset for French

  #36 opened 3 years ago by yongzx
  2

• RuntimeError: [enforce fail at CPUAllocator.cpp:64] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 237414383616 bytes. Error code 12 (Cannot allocate memory)

  #35 opened 4 years ago by keloemma
  3

• Filling masks

  #33 opened 4 years ago by xiaoouwang
  4

• Using the Flaubert for Translation

  #34 opened 4 years ago by kruthikakr
  1

• Finetuning on FLUE

  #32 opened 4 years ago by LisaBanana
  12

• Pretraining with News Crawls by WMT 19

  #31 opened 4 years ago by divkakwani
  1

• weird results on new task using flaubert-large-cased model

  #28 opened 5 years ago by saharghannay
  1

• Update about the coming soon FLUE tasks

  #29 opened 5 years ago by Tixierae
  3

• fastBPE

  #27 opened 5 years ago by Mehdi07
  2

• bug in run_flue.py

  #22 opened 5 years ago by keloemma
  7

• tweet sentiment analysis in french

  #21 opened 5 years ago
  7

• Convert from xlm to Hugging Face

  #19 opened 5 years ago by king-menin
  1

• Model names

  #26 opened 5 years ago by Khasir
  1

• Datasets: EnronSent, Le Monde, PCT

  #25 opened 5 years ago by jchwenger
  2

• Enronsent usage

  #23 opened 5 years ago by JbRemy
  1

• Typo in corpus download

  #24 opened 5 years ago by JbRemy
  1

• RuntimeError: The size of tensor a (68729) must match the size of tensor b (13681) at non-singleton dimension 0

  #20 opened 5 years ago by keloemma
  0

• Erreur de segmentationtd::allocator<std::vector<at::Tensor, std::allocator<at::Tensor> > > >, float) + 0x1679

  #17 opened 5 years ago by keloemma
  0

• fast: fastBPE/fastBPE.hpp:458: void fastBPE::readCodes(const char*, std::unordered_map<std::pair<std::__cxx11::basic_string<char>, std::__cxx11::basic_string<char>

  #16 opened 5 years ago by keloemma
  0

• Import Error

  #15 opened 5 years ago by rcontesti
  5

• 1.get_toolkit.sh

  #5 opened 5 years ago by jourlin
  5

• Model name not found or config.json missing

  #6 opened 5 years ago by hzitoun
  6

• How can I train flaubert on a different corpus (not gutenberg, wiki) but for another domain ?

  #9 opened 5 years ago by keloemma
  11

• Questions related to the finetuning process of Flaubert on a dataset ?

  #11 opened 5 years ago by keloemma
  2

• Can we encode a document from command line?

  #12 opened 5 years ago by dataislife
  1

• Using flauBERT for similarities between sentences

  #7 opened 5 years ago by QuentinSpalla
  3

• Pre-training data for FlauBERT

  #14 opened 5 years ago by manueltonneau
  2

• Little change in the shebang of prepare-data-cls.sh

  #10 opened 5 years ago by penalva34
  1

• dataset in French NLI and STS - like

  #4 opened 5 years ago by dataislife
  15

• model on official transformers model repository

  #3 opened 5 years ago by cedspam
  4

• *Error in `python3': free(): invalid pointer: 0x000055ae110d8c20 ***** Abandon

  #8 opened 5 years ago by keloemma
  2

• error in prepare-data-cls.sh

  #2 opened 5 years ago by brunosez
  1