mimo-v2.6-pro/dflash/config.json

{
  "architectures": [
    "DFlashDraftModel"
  ],
  "model_type": "qwen3",
  "auto_map": {
    "AutoModel": "dflash.DFlashDraftModel"
  },
  "hidden_size": 6144,
  "intermediate_size": 16384,
  "num_hidden_layers": 5,
  "num_attention_heads": 128,
  "num_key_value_heads": 8,
  "head_dim": 128,
  "v_head_dim": 128,
  "partial_rotary_factor": 0.5,
  "block_size": 8,
  "dflash_config": {
    "target_layer_ids": [
      0,
      15,
      31,
      47,
      69
    ],
    "mask_token_id": 151675,
    "num_anchors": 4096,
    "block_size": 8,
    "loss_decay_gamma": 7.0,
    "attention_value_scale": 0.612,
    "attention_sink_bias": true
  },
  "layer_types": [
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention"
  ],
  "sliding_window": 1024,
  "use_sliding_window": true,
  "is_causal": false,
  "num_target_layers": 70,
  "target_hidden_size": 6144,
  "vocab_size": 152576,
  "max_position_embeddings": 1048576,
  "rope_theta": 10000.0,
  "rms_norm_eps": 1e-05,
  "torch_dtype": "bfloat16",
  "hidden_act": "silu",
  "attention_bias": false,
  "attention_dropout": 0.0,
  "add_swa_attention_sink_bias": true,
  "tie_word_embeddings": false,
  "use_cache": true
}