{ "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 ], "auto_map": { "AutoConfig": "configuration_minimax_m2.MiniMaxM2Config", "AutoModelForCausalLM": "modeling_minimax_m2.MiniMaxM2ForCausalLM" }, "bos_token_id": 1, "dtype": "bfloat16", "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 1536, "max_position_embeddings": 204800, "model_type": "minimax_m2", "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": 198, "num_mtp_modules": 3, "output_router_logits": false, "partial_rotary_factor": 0.5, "qk_norm_type": "per_layer", "reap_adaptive_nonuniform_experts": true, "reap_adaptive_retained_experts_by_layer": { "0": 116, "1": 144, "10": 197, "11": 197, "12": 196, "13": 198, "14": 196, "15": 196, "16": 194, "17": 198, "18": 195, "19": 191, "2": 164, "20": 186, "21": 192, "22": 189, "23": 187, "24": 180, "25": 182, "26": 177, "27": 173, "28": 170, "29": 170, "3": 180, "30": 168, "31": 163, "32": 162, "33": 157, "34": 157, "35": 162, "36": 164, "37": 162, "38": 161, "39": 155, "4": 194, "40": 167, "41": 149, "42": 155, "43": 155, "44": 160, "45": 158, "46": 156, "47": 159, "48": 155, "49": 152, "5": 190, "50": 148, "51": 146, "52": 140, "53": 137, "54": 139, "55": 141, "56": 139, "57": 136, "58": 138, "59": 133, "6": 190, "60": 124, "61": 116, "7": 187, "8": 188, "9": 186 }, "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, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.55.0", "use_cache": false, "use_mtp": true, "use_qk_norm": true, "use_routing_bias": true, "vocab_size": 200064 }