This is a GptOss 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: gpt_oss_backbone
- trainable: True
- dtype: {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}
- vocabulary_size: 201088
- num_layers: 24
- num_query_heads: 64
- hidden_dim: 2880
- intermediate_dim: 2880
- num_experts: 32
- top_k: 4
- rope_max_wavelength: 150000
- rope_scaling_factor: 32.0
- num_key_value_heads: 8
- sliding_window: 128
- layer_norm_epsilon: 1e-05
- dropout: 0
- output_router_logits: False
- head_dim: 64
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