vicuna_1.5_7b_en / README.md
Divyasreepat's picture
Upload folder using huggingface_hub
9b9f1c1 verified
|
raw
history blame
732 Bytes
metadata
library_name: keras-hub

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

  • name: llama_backbone_1
  • trainable: True
  • vocabulary_size: 32000
  • num_layers: 32
  • num_query_heads: 32
  • hidden_dim: 4096
  • intermediate_dim: 11008
  • rope_max_wavelength: 10000.0
  • rope_scaling_factor: 1.0
  • num_key_value_heads: 32
  • layer_norm_epsilon: 1e-05
  • dropout: 0

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