{
  "ada_dlm_loss_ratio": null,
  "ada_perm_ratio_global": null,
  "ada_perm_ratio_per_block": null,
  "adaptive_mask_rate": false,
  "always_mask_im_end": false,
  "ar_loss_weight": 1.0,
  "architectures": [
    "NemotronLabsDiffusionVLMModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_implementation": null,
  "auto_map": {
    "AutoConfig": "configuration_nemotron_labs_diffusion_vlm.NemotronLabsDiffusionVLMConfig",
    "AutoModel": "modeling_nemotron_labs_diffusion_vlm.NemotronLabsDiffusionVLMModel",
    "AutoModelForCausalLM": "modeling_nemotron_labs_diffusion_vlm.NemotronLabsDiffusionVLMModel"
  },
  "block_size": 32,
  "bos_token_id": 1,
  "complementary_mask": true,
  "diff_loss_weight": 0.5,
  "dlm_arch": "encoder",
  "dlm_loss_weight": 0.5,
  "dlm_paradigm": "bidirectional",
  "dlm_type": "llada",
  "dp_varying_mask_ratio": false,
  "dtype": "bfloat16",
  "enforce_mask": false,
  "eos_token_id": 11,
  "global_loss_avg": true,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "im_end_token_id": 11,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "mask_token_id": 100,
  "max_position_embeddings": 262144,
  "mlp_bias": false,
  "model_type": "nemotron_labs_diffusion_vlm",
  "multi_sampling": null,
  "multimodal_projector_bias": false,
  "num_ar_layers": 0,
  "num_attention_heads": 32,
  "num_diffusion_layers": 0,
  "num_hidden_layers": 34,
  "num_key_value_heads": 8,
  "num_skip_loss_tokens": 0,
  "pad_token_id": 11,
  "prefix_ratio": 0.8,
  "projector_hidden_act": "gelu",
  "random_length_prob": 0,
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 16.0,
    "llama_4_scaling_beta": 0.1,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "original_max_position_embeddings": 16384,
    "rope_theta": 1000000.0,
    "rope_type": "yarn",
    "type": "yarn"
  },
  "rope_scaling": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 16.0,
    "llama_4_scaling_beta": 0.1,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "original_max_position_embeddings": 16384,
    "rope_theta": 1000000.0,
    "rope_type": "yarn",
    "type": "yarn"
  },
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "spatial_merge_size": 2,
  "tie_word_embeddings": false,
  "tok_mask_half_life_ratio": null,
  "transformers_version": "4.57.1",
  "use_cache": false,
  "vision_config": {
    "attention_dropout": 0.0,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "image_size": 1540,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "model_type": "pixtral",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "rope_parameters": {
      "rope_theta": 10000.0,
      "rope_type": "default"
    }
  },
  "vision_feature_layer": -1,
  "vocab_size": 131073
}