| { | |
| "module": "keras_hub.src.models.modern_bert.modern_bert_backbone", | |
| "class_name": "ModernBertBackbone", | |
| "config": { | |
| "name": "modern_bert_backbone", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "vocabulary_size": 50368, | |
| "hidden_dim": 1024, | |
| "intermediate_dim": 2624, | |
| "num_layers": 28, | |
| "num_heads": 16, | |
| "local_attention_window": 128, | |
| "global_attn_every_n_layers": 3, | |
| "rotary_max_wavelength": 160000.0, | |
| "local_rotary_max_wavelength": 10000.0, | |
| "layer_norm_epsilon": 1e-05 | |
| }, | |
| "registered_name": "keras_hub>ModernBertBackbone" | |
| } |