This is a RWKV7 model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends. Model config:

  • name: rwkv7_backbone
  • trainable: True
  • dtype: {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}
  • hidden_size: 1024
  • head_size: 64
  • gate_lora: 128
  • mv_lora: 32
  • aaa_lora: 64
  • decay_lora: 64
  • vocabulary_size: 65536
  • dropout_rate: 0
  • intermediate_dim: 4096
  • num_layers: 24

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
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including keras/rwkv7_g1a_0.3b