metadata
library_name: keras-hub
pipeline_tag: text-generation
This is a Llama3 model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
This model is related to a CausalLM task.
Model config:
- name: llama3_backbone
- trainable: True
- vocabulary_size: 128256
- num_layers: 16
- num_query_heads: 32
- hidden_dim: 2048
- intermediate_dim: 8192
- rope_max_wavelength: 500000.0
- rope_position_scaling_factor: 1
- rope_frequency_adjustment_factor: 32
- rope_low_freq_factor: 1
- rope_high_freq_factor: 4
- rope_pretraining_sequence_length: 8192
- num_key_value_heads: 8
- 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.