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": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": "static",
          "block_structure": null,
          "dynamic": false,
          "group_size": 128,
          "num_bits": 4,
          "observer": "mse",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "group",
          "symmetric": true,
          "type": "int",
          "zp_dtype": null
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.14.0.1"
  },
  "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": "4.57.6",
  "use_cache": true,
  "use_mtp": true,
  "use_qk_norm": true,
  "use_routing_bias": true,
  "vocab_size": 200064
}