t5_large_multi / README.md
Divyasreepat's picture
Upload folder using huggingface_hub
8e11e8c verified
|
raw
history blame
737 Bytes
metadata
library_name: keras-hub

This is a T5 model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends. Model config:

  • name: t5_backbone
  • trainable: True
  • vocabulary_size: 32128
  • hidden_dim: 1024
  • intermediate_dim: 4096
  • num_layers: 24
  • num_heads: 16
  • activation: relu
  • key_value_dim: None
  • dropout: 0.1
  • use_gated_activation: False
  • layer_norm_epsilon: 1e-06
  • tie_embedding_weights: True

This model card has been generated automatically and should be completed by the model author. See Model Cards documentation for more information.