| { | |
| "module": "keras_hub.src.models.qwen.qwen_backbone", | |
| "class_name": "QwenBackbone", | |
| "config": { | |
| "name": "qwen_backbone", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "vocabulary_size": 151936, | |
| "num_layers": 24, | |
| "num_query_heads": 14, | |
| "hidden_dim": 896, | |
| "intermediate_dim": 4864, | |
| "rope_max_wavelength": 1000000.0, | |
| "rope_scaling_factor": 1.0, | |
| "num_key_value_heads": 2, | |
| "layer_norm_epsilon": 1e-06, | |
| "dropout": 0, | |
| "tie_word_embeddings": true, | |
| "use_sliding_window_attention": false, | |
| "sliding_window_size": 32768 | |
| }, | |
| "registered_name": "keras_hub>QwenBackbone" | |
| } |