| { | |
| "model_type": "privacy_filter", | |
| "inference_contract_version": 1, | |
| "encoding": "o200k_base", | |
| "num_hidden_layers": 8, | |
| "num_experts": 128, | |
| "experts_per_token": 4, | |
| "vocab_size": 200064, | |
| "num_labels": 33, | |
| "hidden_size": 640, | |
| "intermediate_size": 640, | |
| "head_dim": 64, | |
| "num_attention_heads": 14, | |
| "num_key_value_heads": 2, | |
| "sliding_window": 257, | |
| "bidirectional_context": true, | |
| "bidirectional_left_context": 128, | |
| "bidirectional_right_context": 128, | |
| "initial_context_length": 4096, | |
| "max_position_embeddings": 131072, | |
| "default_n_ctx": 128000, | |
| "rope_theta": 150000, | |
| "rope_scaling_factor": 32.0, | |
| "rope_ntk_alpha": 1.0, | |
| "rope_ntk_beta": 32.0, | |
| "param_dtype": "bfloat16" | |
| } |