config.json

{
  "add_faster_video": false,
  "add_time_instruction": false,
  "anneal_start_block_size": 1,
  "architectures": [
    "DiffusionVL_Qwen2_5_ForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bd3lm_antithetic_sampling": true,
  "bd3lm_attn_backend": "sdpa",
  "bd3lm_block_aligned_eos": true,
  "bd3lm_block_size": 8,
  "bd3lm_complementary_mask": false,
  "bd3lm_cross_attn": true,
  "bd3lm_ignore_bos": true,
  "bd3lm_noise_granularity": "block",
  "bd3lm_noise_type": "loglinear",
  "bd3lm_parameterization": "subs",
  "bd3lm_resample": false,
  "bd3lm_sampling_eps_max": 1.0,
  "bd3lm_sampling_eps_min": 0.001,
  "bd3lm_time_conditioning": false,
  "bd3lm_token_shift_prediction": false,
  "bd3lm_var_min": true,
  "bos_token_id": 151643,
  "enable_bd3lm": true,
  "enable_block_size_annealing": false,
  "enable_noise_level_annealing": false,
  "eos_token_id": 151645,
  "faster_token_stride": 10,
  "force_sample": false,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_aspect_ratio": "anyres_max_4",
  "image_crop_resolution": null,
  "image_grid_pinpoints": [
    [
      384,
      384
    ],
    [
      384,
      768
    ],
    [
      384,
      1152
    ],
    [
      384,
      1536
    ],
    [
      384,
      1920
    ],
    [
      384,
      2304
    ],
    [
      768,
      384
    ],
    [
      768,
      768
    ],
    [
      768,
      1152
    ],
    [
      768,
      1536
    ],
    [
      768,
      1920
    ],
    [
      768,
      2304
    ],
    [
      1152,
      384
    ],
    [
      1152,
      768
    ],
    [
      1152,
      1152
    ],
    [
      1152,
      1536
    ],
    [
      1152,
      1920
    ],
    [
      1152,
      2304
    ],
    [
      1536,
      384
    ],
    [
      1536,
      768
    ],
    [
      1536,
      1152
    ],
    [
      1536,
      1536
    ],
    [
      1536,
      1920
    ],
    [
      1536,
      2304
    ],
    [
      1920,
      384
    ],
    [
      1920,
      768
    ],
    [
      1920,
      1152
    ],
    [
      1920,
      1536
    ],
    [
      1920,
      1920
    ],
    [
      1920,
      2304
    ],
    [
      2304,
      384
    ],
    [
      2304,
      768
    ],
    [
      2304,
      1152
    ],
    [
      2304,
      1536
    ],
    [
      2304,
      1920
    ],
    [
      2304,
      2304
    ]
  ],
  "image_split_resolution": null,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_pixels": 262144,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "min_pixels": 147456,
  "mm_hidden_size": 1152,
  "mm_newline_position": "grid",
  "mm_patch_merge_type": "spatial_unpad",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "mm_spatial_pool_mode": "bilinear",
  "mm_spatial_pool_stride": null,
  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "google/siglip2-so400m-patch14-384",
  "mm_vision_tower_lr": 2e-06,
  "model_max_length": 8192,
  "model_type": "diffusionvl_qwen",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "pos_skipping_range": 4096,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 8192,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.0",
  "use_cache": true,
  "use_mm_proj": true,
  "use_pos_skipping": false,
  "use_sliding_window": false,
  "vision_tower_pretrained": null,
  "vocab_size": 152064,
  "mask_token_id": 151671,
  "vision_config": {
    "hidden_size": 1152,
    "intermediate_size": 4304,
    "num_hidden_layers": 26,
    "num_attention_heads": 16,
    "num_channels": 3,
    "image_size": 384,
    "patch_size": 14,
    "hidden_act": "gelu_pytorch_tanh",
    "layer_norm_eps": 1e-06,
    "attention_dropout": 0.0
  },
  "auto_map": {
    "AutoConfig": "configuration_diffusionvl_qwen2_5.DiffusionVL_Qwen2_5_Config",
    "AutoModelForCausalLM": "modeling_diffusionvl_qwen2_5.DiffusionVL_Qwen2_5_ForConditionalGeneration",
    "AutoProcessor": "processing_diffusionvl_qwen2_5.DiffusionVL_Qwen2_5_Processor"
  }
}