config.json

{
  "architectures": [
    "Qwen2VLVAEForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "vision_start_token_id": 151652,
  "vision_end_token_id": 151653,
  "vision_token_id": 151654,
  "image_token_id": 151655,
  "video_token_id": 151656,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2_vl_vae",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vision_config": {
    "in_channels": 12,
    "patch_size": 2,
    "hidden_size": 3584,
    "vae_path": "genmo/mochi-1-preview",
    "vae_subfolder": "vae",
    "vae_config": {
      "_class_name": "AutoencoderKLMochi",
      "_diffusers_version": "0.32.0.dev0",
      "act_fn": "silu",
      "add_attention_block": [
        false,
        true,
        true,
        true,
        true
      ],
      "decoder_block_out_channels": [
        128,
        256,
        512,
        768
      ],
      "encoder_block_out_channels": [
        64,
        128,
        256,
        384
      ],
      "in_channels": 15,
      "latent_channels": 12,
      "latents_mean": [
        -0.06730895953510081,
        -0.038011381506090416,
        -0.07477820912866141,
        -0.05565264470995561,
        0.012767231469026969,
        -0.04703542746246419,
        0.043896967884726704,
        -0.09346305707025976,
        -0.09918314763016893,
        -0.008729793427399178,
        -0.011931556316503654,
        -0.0321993391887285
      ],
      "latents_std": [
        0.9263795028493863,
        0.9248894543193766,
        0.9393059390890617,
        0.959253732819592,
        0.8244560132752793,
        0.917259975397747,
        0.9294154431013696,
        1.3720942357788521,
        0.881393668867029,
        0.9168315692124348,
        0.9185249279345552,
        0.9274757570805041
      ],
      "layers_per_block": [
        3,
        3,
        4,
        6,
        3
      ],
      "out_channels": 3,
      "scaling_factor": 1.0,
      "spatial_expansions": [
        2,
        2,
        2
      ],
      "temporal_expansions": [
        1,
        2,
        3
      ]
    }
  },
  "rope_scaling": {
    "type": "mrope",
    "mrope_section": [
      16,
      24,
      24
    ]
  },
  "vocab_size": 152064
}