| { | |
| "architectures": [ | |
| "ArmoRMForSequenceClassification" | |
| ], | |
| "model_type": "armorm", | |
| "vocab_size": 128256, | |
| "hidden_size": 4096, | |
| "intermediate_size": 14336, | |
| "num_hidden_layers": 32, | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 8, | |
| "hidden_act": "silu", | |
| "max_position_embeddings": 131072, | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-05, | |
| "use_cache": true, | |
| "rope_theta": 500000.0, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "mlp_bias": false, | |
| "num_objectives": 5, | |
| "objective_names": [ | |
| "statute_reference", | |
| "legal_accuracy", | |
| "case_law_reference", | |
| "linguistic_coherence", | |
| "depth_coverage" | |
| ], | |
| "gating_hidden_dim": 1024, | |
| "gating_num_layers": 4, | |
| "temperature": 10.0, | |
| "torch_dtype": "bfloat16", | |
| "auto_map": { | |
| "AutoConfig": "modeling_armorm.ArmoRMConfig", | |
| "AutoModelForSequenceClassification": "modeling_armorm.ArmoRMForSequenceClassification" | |
| } | |
| } |