huggingface/tflite-android-transformers

Issues

• unrecognized FlexErf node in downloaded tflite model

  #13 opened 4 years ago by devandong
  2

• Are there any resources or documentation on how to integrate the tokenization part into Android?

  #18 opened 2 years ago by BENSAFOUAN-Abdelhalim
  2

• Has the demo gif for text generation been sped up?

  #12 opened 4 years ago by farazk86
  1

• Any ideas on how we can convert a model from huggingface (transformers library )to tensorflow lite?

  #17 opened 2 years ago by BENSAFOUAN-Abdelhalim
  0

• When I set the input dimension to [1384], I get [3,5]

  #16 opened 3 years ago by songdlut
  0

• model generated by model_generation but not able to invoke.

  #5 opened 5 years ago by o20021106
  4

• GPT2 error : ByteBuffer is not a valid flatbuffer model

  #15 opened 4 years ago by jason9693
  0

• How would one go about using the tflite on ordinary linux?

  #14 opened 4 years ago
  0

• float16 quantized DistilBERT model results into performance drop

  #11 opened 4 years ago by sayakpaul
  0

• Discrepencies for a fine-tuned DistilBERT model

  #10 opened 4 years ago by sayakpaul
  0

• How to run tflite models on Linux?

  #9 opened 4 years ago by Mo-Abdelgawad
  0

• Can anyone give me the Android app apk file of distill GPT 2

  #7 opened 5 years ago by danish9129
  1

• model generation got error

  #2 opened 5 years ago by gitathrun
  3

• Would like support for a superfast model for gpt2

  #6 opened 5 years ago by Peter-Devine
  0

• Support BERT finetuned on SQuAD

  #1 opened 5 years ago by Pierrci
  3

• How to make FP16 quantization on gpt/xl?

  #4 opened 5 years ago by Archelunch
  4