This is a Bert model uploaded using the KerasNLP library and can be used with JAX, TensorFlow, and PyTorch backends.
This model is related to a Classifier task.
Model config:
- name: bert_backbone
- trainable: True
- vocabulary_size: 30522
- num_layers: 2
- num_heads: 2
- hidden_dim: 128
- intermediate_dim: 512
- dropout: 0.1
- max_sequence_length: 512
- num_segments: 2
This model card has been generated automatically and should be completed by the model author. See Model Cards documentation for more information.
- Downloads last month
- 5
Inference API (serverless) does not yet support keras-nlp models for this pipeline type.