config.json

{
  "add_faster_video": false,
  "add_time_instruction": false,
  "anneal_start_block_size": 1,
  "architectures": [
    "DiffusionVL_Qwen2_5_VL_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_mask_prob": 0.5,
  "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_mtd": false,
  "enable_noise_level_annealing": false,
  "eos_token_id": 151645,
  "faster_token_stride": 10,
  "force_sample": false,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "image_aspect_ratio": "pad",
  "image_crop_resolution": null,
  "image_grid_pinpoints": null,
  "image_split_resolution": null,
  "image_token_id": null,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "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",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_pixels": 262144,
  "max_position_embeddings": 128000,
  "max_window_layers": 70,
  "min_pixels": 147456,
  "mm_hidden_size": 1280,
  "mm_newline_position": "grid",
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": null,
  "mm_projector_type": "qwen_merger",
  "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": "/path/to/Qwen2.5-VL-3B-Instruct-DiffusionVL",
  "mm_vision_tower_lr": 2e-06,
  "model_max_length": 8192,
  "model_type": "diffusionvl_qwenvl",
  "num_attention_heads": 16,
  "num_hidden_layers": 36,
  "num_key_value_heads": 2,
  "pos_skipping_range": 4096,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "mrope_section": [
      16,
      24,
      24
    ],
    "rope_type": "default",
    "type": "default"
  },
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "text_config": {
    "architectures": [
      "Qwen2_5_VLForConditionalGeneration"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "image_token_id": null,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "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",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 128000,
    "max_window_layers": 70,
    "model_type": "qwen2_5_vl_text",
    "num_attention_heads": 16,
    "num_hidden_layers": 36,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-06,
    "rope_scaling": {
      "mrope_section": [
        16,
        24,
        24
      ],
      "rope_type": "default",
      "type": "default"
    },
    "rope_theta": 1000000.0,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "torch_dtype": "float32",
    "use_cache": true,
    "use_sliding_window": false,
    "video_token_id": null,
    "vision_end_token_id": 151653,
    "vision_start_token_id": 151652,
    "vision_token_id": 151654,
    "vocab_size": 151936
  },
  "tie_word_embeddings": true,
  "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,
  "video_token_id": null,
  "vision_config": {
    "depth": 32,
    "fullatt_block_indexes": [
      7,
      15,
      23,
      31
    ],
    "hidden_act": "silu",
    "hidden_size": 1280,
    "in_channels": 3,
    "in_chans": 3,
    "initializer_range": 0.02,
    "intermediate_size": 3420,
    "model_type": "",
    "num_heads": 16,
    "out_hidden_size": 2048,
    "patch_size": 14,
    "spatial_merge_size": 2,
    "spatial_patch_size": 14,
    "temporal_patch_size": 2,
    "tokens_per_second": 2,
    "torch_dtype": "float32",
    "window_size": 112
  },
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "vision_token_id": 151654,
  "vision_tower_pretrained": null,
  "vocab_size": 151936,
  "mask_token_id": 151671,
  "auto_map": {
    "AutoConfig": "configuration_diffusionvl_qwen2_5_vl.DiffusionVL_Qwen2_5_VL_Config",
    "AutoModelForCausalLM": "modeling_diffusionvl_qwen2_5_vl.DiffusionVL_Qwen2_5_VL_ForConditionalGeneration",
    "AutoProcessor": "processing_diffusionvl_qwen2_5_vl.DiffusionVL_Qwen2_5_VL_Processor"
  }
}