Commit History

  1. model and quantized model both with attention

    Liman
    56bbff3

  1. replace fp32 model with one with attention layers

    Liman
    1dc2600
  2. onnx model with attention

    Liman
    af82537

  1. include output_attentions in tokenizer_config.json

    Liman
    b5158fd
  2. include output_attentions config in config.json

    Liman
    48ebe5a

  1. rename q8 model

    Liman
    1b1a2ec
  2. add quantized models

    Liman
    7187111

  1. Imported model from jaxmef repo

    Liman
    71772cd
  2. initial commit

    Verified signature
    e960c98