config.json

{
  "alignment": false,
  "architectures": [
    "VRT_Qwen2VLForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "depth_action_id": null,
  "depth_action_start_id": null,
  "depth_image_token_id": null,
  "detection_action_id": null,
  "detection_action_start_id": null,
  "detection_image_token_id": null,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "image_token_id": 151655,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen2_vl_vpt",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_inner_forward_run": 1,
  "num_key_value_heads": 2,
  "para_end_id": 151645,
  "para_mask_id": 0,
  "para_mask_ratio": 0.0,
  "para_start_id": 151644,
  "projector_scale": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "mrope_section": [
      16,
      24,
      24
    ],
    "rope_type": "default",
    "type": "default"
  },
  "rope_theta": 1000000.0,
  "seg_action_id": null,
  "seg_action_start_id": null,
  "seg_image_token_id": 151657,
  "sliding_window": 32768,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.45.2",
  "use_cache": false,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_config": {
    "hidden_size": 1536,
    "in_chans": 3,
    "model_type": "qwen2_vl",
    "spatial_patch_size": 14
  },
  "vision_encoder_ls": [
    "sam"
  ],
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "vision_token_id": 151654,
  "vocab_size": 151936
}