{
  "architectures": [
    "DFlashDraftModel"
  ],
  "model_type": "qwen3",
  "block_size": 16,
  "num_target_layers": 47,
  "dflash_config": {
    "mask_token_id": 154821,
    "target_layer_ids": [
      1,
      12,
      23,
      33,
      44
    ],
    "causal": false,
    "use_aux_hidden_state": true,
    "prediction_shifted": true
  },
  "hidden_size": 2048,
  "num_hidden_layers": 8,
  "num_attention_heads": 32,
  "num_key_value_heads": 4,
  "head_dim": 128,
  "intermediate_size": 6144,
  "hidden_act": "silu",
  "rms_norm_eps": 1e-06,
  "vocab_size": 154880,
  "draft_vocab_size": 154880,
  "max_position_embeddings": 202752,
  "rope_theta": 1000000.0,
  "attention_bias": false,
  "attention_dropout": 0.0,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "tie_word_embeddings": false,
  "dtype": "bfloat16",
  "pad_token_id": 154820,
  "eos_token_id": 154820,
  "_converted_from": "/pscratch/sd/d/dfarough/LLMs/dflash/checkpoints/dflash-glm47/dflash_block16_glm47_flash/step_2916"
}