| { | |
| "alpha_init": 1.0, | |
| "architectures": [ | |
| "MoAMetricLM" | |
| ], | |
| "attn_drop": 0.1, | |
| "attn_heads": 32, | |
| "bos_token_id": 101, | |
| "conv_kernel": 5, | |
| "conv_mult": 2, | |
| "dim": 1024, | |
| "discrepancy_modulation": true, | |
| "drop_path": 0.0, | |
| "dtype": "float32", | |
| "enable_feature_gates": true, | |
| "enable_router_gates": true, | |
| "energy_amplification": 0.1, | |
| "eos_token_id": 102, | |
| "ff_mult": 4, | |
| "ffn_hidden": 2048, | |
| "head_feature_heads": 8, | |
| "layer_scale_init_value": 0.0001, | |
| "learn_alpha": true, | |
| "learn_radius": true, | |
| "lr_rank": 32, | |
| "maha_init": 1.0, | |
| "max_position_embeddings": 1024, | |
| "max_seq_len_cached": 8192, | |
| "metric": "l2", | |
| "mixer_hidden": 2048, | |
| "model_type": "moa_metric", | |
| "mqa_q_heads": 64, | |
| "n_branches": 3, | |
| "n_token_router_heads": 4, | |
| "num_hidden_layers": 6, | |
| "num_layers": 6, | |
| "origin_init_scale": 0.0, | |
| "pad_token_id": 0, | |
| "proj_drop": 0.1, | |
| "r_basis": 16, | |
| "radius_init": 3.0, | |
| "router_bias_heads": 4, | |
| "router_dropout": 0.1, | |
| "router_hidden": 2048, | |
| "router_init_temperature": 2.0, | |
| "router_temperature": 1.0, | |
| "router_topk": 2, | |
| "shared_kv_ratio": 0.5, | |
| "theta_base": 10000.0, | |
| "ti_reg_samples": 0, | |
| "ti_reg_weight": 0.0, | |
| "transformers_version": "4.56.1", | |
| "use_balls": true, | |
| "vocab_size": 50257 | |
| } | |