{
  "adaptive_mask_rate": false,
  "architectures": [
    "EfficientDLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_implementation": "sdpa",
  "auto_map": {
    "AutoConfig": "configuration_edlm.EfficientDLMConfig",
    "AutoModel": "modeling_edlm.EfficientDLM"
  },
  "block_size": 32,
  "diff_loss_weight": 1,
  "disable_qk_norm": false,
  "dlm_arch": "encoder",
  "dlm_paradigm": "bidirectional",
  "dlm_type": "llada",
  "enforce_mask": false,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 9728,
  "intl_mask": false,
  "mask_token_id": 151662,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen3",
  "multi_sampling": null,
  "num_ar_layers": 0,
  "num_attention_heads": 32,
  "num_diffusion_layers": 0,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "prefix_ratio": 0.8,
  "random_length_prob": 0,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tok_mask_half_life_ratio": null,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.52.2",
  "use_cache": false,
  "use_sliding_window": false,
  "vocab_size": 151936
}