This is a Qwen3 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: qwen3_backbone
- trainable: True
- vocabulary_size: 151936
- num_layers: 40
- num_query_heads: 40
- hidden_dim: 5120
- head_dim: 128
- intermediate_dim: 17408
- rope_max_wavelength: 1000000
- rope_scaling_factor: 1.0
- num_key_value_heads: 8
- layer_norm_epsilon: 1e-06
- dropout: 0.0
- tie_word_embeddings: False
- sliding_window_size: None
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
- 9