config.json

{
  "architectures": [
    "UnivaQwen2p5VLForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "decay": 0.999,
  "denoise_tower": {
    "_attn_implementation_autoset": true,
    "denoise_projector_type": "mlp2x_gelu",
    "denoiser_config": {
      "_class_name": "FluxTransformer2DModel",
      "_diffusers_version": "0.30.0.dev0",
      "_name_or_path": "../checkpoints/flux-dev/transformer",
      "attention_head_dim": 128,
      "guidance_embeds": true,
      "in_channels": 64,
      "joint_attention_dim": 4096,
      "num_attention_heads": 24,
      "num_layers": 19,
      "num_single_layers": 38,
      "patch_size": 1,
      "pooled_projection_dim": 768
    },
    "denoiser_type": "flux",
    "input_hidden_size": 3584,
    "model_type": "univa_denoise_tower",
    "output_hidden_size": 4096,
    "torch_dtype": "float32",
    "vae_input_hidden_size": 64,
    "vae_projector_type": "mlp2x_gelu"
  },
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_begin_token_id": 151652,
  "image_end_token_id": 151653,
  "image_token_id": 151655,
  "image_token_length": null,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "inv_gamma": 1.0,
  "max_position_embeddings": 128000,
  "max_window_layers": 28,
  "min_decay": 0.0,
  "model_type": "univa_qwen2p5vl",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "optimization_step": 40000,
  "power": 0.6666666666666666,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "mrope_section": [
      16,
      24,
      24
    ],
    "rope_type": "default",
    "type": "default"
  },
  "rope_theta": 1000000.0,
  "shortcut_image_embeds": false,
  "shortcut_image_embeds_scale": 0.5,
  "shortcut_projector_type": null,
  "sliding_window": 32768,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.50.0",
  "update_after_step": 0,
  "use_cache": true,
  "use_ema_warmup": false,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_config": {
    "depth": 32,
    "fullatt_block_indexes": [
      7,
      15,
      23,
      31
    ],
    "hidden_act": "silu",
    "hidden_size": 1280,
    "in_channels": 3,
    "in_chans": 3,
    "intermediate_size": 3420,
    "model_type": "qwen2_5_vl",
    "num_heads": 16,
    "out_hidden_size": 3584,
    "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,
  "vocab_size": 152064
}