config.json

{
  "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": 196608,
  "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": 256,
  "num_mtp_modules": 3,
  "output_router_logits": false,
  "partial_rotary_factor": 0.5,
  "qk_norm_type": "per_layer",
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "nvfp4-pack-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": "local",
          "group_size": 16,
          "num_bits": 4,
          "observer": "static_minmax",
          "observer_kwargs": {},
          "strategy": "tensor_group",
          "symmetric": true,
          "type": "float"
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": 16,
          "num_bits": 4,
          "observer": "static_minmax",
          "observer_kwargs": {},
          "strategy": "tensor_group",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "nvfp4-pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.layers.0.block_sparse_moe.gate",
      "model.layers.1.block_sparse_moe.gate",
      "model.layers.2.block_sparse_moe.gate",
      "model.layers.3.block_sparse_moe.gate",
      "model.layers.4.block_sparse_moe.gate",
      "model.layers.5.block_sparse_moe.gate",
      "model.layers.6.block_sparse_moe.gate",
      "model.layers.7.block_sparse_moe.gate",
      "model.layers.8.block_sparse_moe.gate",
      "model.layers.9.block_sparse_moe.gate",
      "model.layers.10.block_sparse_moe.gate",
      "model.layers.11.block_sparse_moe.gate",
      "model.layers.12.block_sparse_moe.gate",
      "model.layers.13.block_sparse_moe.gate",
      "model.layers.14.block_sparse_moe.gate",
      "model.layers.15.block_sparse_moe.gate",
      "model.layers.16.block_sparse_moe.gate",
      "model.layers.17.block_sparse_moe.gate",
      "model.layers.18.block_sparse_moe.gate",
      "model.layers.19.block_sparse_moe.gate",
      "model.layers.20.block_sparse_moe.gate",
      "model.layers.21.block_sparse_moe.gate",
      "model.layers.22.block_sparse_moe.gate",
      "model.layers.23.block_sparse_moe.gate",
      "model.layers.24.block_sparse_moe.gate",
      "model.layers.25.block_sparse_moe.gate",
      "model.layers.26.block_sparse_moe.gate",
      "model.layers.27.block_sparse_moe.gate",
      "model.layers.28.block_sparse_moe.gate",
      "model.layers.29.block_sparse_moe.gate",
      "model.layers.30.block_sparse_moe.gate",
      "model.layers.31.block_sparse_moe.gate",
      "model.layers.32.block_sparse_moe.gate",
      "model.layers.33.block_sparse_moe.gate",
      "model.layers.34.block_sparse_moe.gate",
      "model.layers.35.block_sparse_moe.gate",
      "model.layers.36.block_sparse_moe.gate",
      "model.layers.37.block_sparse_moe.gate",
      "model.layers.38.block_sparse_moe.gate",
      "model.layers.39.block_sparse_moe.gate",
      "model.layers.40.block_sparse_moe.gate",
      "model.layers.41.block_sparse_moe.gate",
      "model.layers.42.block_sparse_moe.gate",
      "model.layers.43.block_sparse_moe.gate",
      "model.layers.44.block_sparse_moe.gate",
      "model.layers.45.block_sparse_moe.gate",
      "model.layers.46.block_sparse_moe.gate",
      "model.layers.47.block_sparse_moe.gate",
      "model.layers.48.block_sparse_moe.gate",
      "model.layers.49.block_sparse_moe.gate",
      "model.layers.50.block_sparse_moe.gate",
      "model.layers.51.block_sparse_moe.gate",
      "model.layers.52.block_sparse_moe.gate",
      "model.layers.53.block_sparse_moe.gate",
      "model.layers.54.block_sparse_moe.gate",
      "model.layers.55.block_sparse_moe.gate",
      "model.layers.56.block_sparse_moe.gate",
      "model.layers.57.block_sparse_moe.gate",
      "model.layers.58.block_sparse_moe.gate",
      "model.layers.59.block_sparse_moe.gate",
      "model.layers.60.block_sparse_moe.gate",
      "model.layers.61.block_sparse_moe.gate",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.13.0"
  },
  "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,
  "transformers_version": "4.57.3",
  "use_cache": true,
  "use_mtp": true,
  "use_qk_norm": true,
  "use_routing_bias": true,
  "vocab_size": 200064
}