keras/qwen2.5_coder_instruct_32b

This is a Qwen 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: qwen_backbone
• trainable: True
• dtype: {'module': 'keras', 'class_name': 'DTypePolicy', 'config': {'name': 'float32'}, 'registered_name': None}
• vocabulary_size: 152064
• num_layers: 64
• num_query_heads: 40
• hidden_dim: 5120
• intermediate_dim: 27648
• rope_max_wavelength: 1000000.0
• rope_scaling_factor: 1.0
• num_key_value_heads: 8
• layer_norm_epsilon: 1e-06
• dropout: 0
• tie_word_embeddings: False
• use_sliding_window_attention: False
• sliding_window_size: 131072

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