“Llama 3.2 in Keras”
martin-gorner
• • 13This 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_2
- trainable: True
- vocabulary_size: 128256
- num_layers: 16
- num_query_heads: 32
- hidden_dim: 2048
- intermediate_dim: 8192
- rope_max_wavelength: 10000
- rope_scaling_factor: 1.0
- num_key_value_heads: 8
- layer_norm_epsilon: 1e-06
- dropout: 0
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
- 14
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://martin-gorner/llama-3.2-1B-pirate-instruct")