| { | |
| "architectures": [ | |
| "MiniMaxM2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attn_type_list": [ | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1, | |
| 1 | |
| ], | |
| "bos_token_id": null, | |
| "eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "layernorm_full_attention_beta": 1.0, | |
| "layernorm_linear_attention_beta": 1.0, | |
| "layernorm_mlp_beta": 1.0, | |
| "max_position_embeddings": 196608, | |
| "mlp_intermediate_size": 8192, | |
| "model_type": "minimax", | |
| "mtp_transformer_layers": 1, | |
| "num_attention_heads": 48, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 62, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 256, | |
| "num_mtp_modules": 3, | |
| "output_router_logits": false, | |
| "qk_norm_type": "per_layer", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 3, | |
| "mode": "affine", | |
| "model.layers.0.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.1.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.2.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.3.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.4.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.5.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.6.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.7.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.8.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.9.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.10.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.11.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.12.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.13.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.14.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.15.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.16.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.17.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.18.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.19.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.20.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.21.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.22.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.23.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.24.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.25.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.26.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.27.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.28.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.29.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.30.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.31.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.32.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.33.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.34.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.35.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.36.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.37.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.38.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.39.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.40.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.41.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.42.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.43.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.44.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.45.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.46.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.47.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.48.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.49.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.50.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.51.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.52.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.53.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.54.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.55.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.56.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.57.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.58.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.59.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.60.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.61.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 3, | |
| "mode": "affine", | |
| "model.layers.0.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.1.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.2.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.3.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.4.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.5.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.6.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.7.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.8.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.9.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.10.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.11.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.12.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.13.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.14.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.15.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.16.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.17.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.18.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.19.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.20.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.21.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.22.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.23.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.24.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.25.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.26.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.27.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.28.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.29.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.30.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.31.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.32.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.33.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.34.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.35.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.36.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.37.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.38.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.39.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.40.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.41.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.42.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.43.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.44.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.45.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.46.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.47.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.48.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.49.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.50.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.51.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.52.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.53.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.54.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.55.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.56.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.57.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.58.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.59.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.60.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.61.block_sparse_moe.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 5000000, | |
| "rotary_dim": 64, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "scoring_func": "sigmoid", | |
| "shared_intermediate_size": 0, | |
| "shared_moe_mode": "sigmoid", | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.46.1", | |
| "use_cache": true, | |
| "use_mtp": true, | |
| "use_qk_norm": true, | |
| "use_routing_bias": true, | |
| "vocab_size": 200064 | |
| } |