config.json

{
  "architectures": [
    "LlavaOnevisionForConditionalGeneration"
  ],
  "dtype": "float16",
  "ignore_index": -100,
  "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_token_index": 151646,
  "model_type": "llava_onevision",
  "multimodal_projector_bias": true,
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "dtype": "bfloat16",
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 896,
    "initializer_range": 0.02,
    "intermediate_size": 4864,
    "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"
    ],
    "max_position_embeddings": 32768,
    "max_window_layers": 24,
    "model_type": "qwen2",
    "num_attention_heads": 14,
    "num_hidden_layers": 24,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 152000
  },
  "tie_word_embeddings": false,
  "transformers_version": "4.56.1",
  "use_image_newline_parameter": true,
  "video_token_index": 151647,
  "vision_aspect_ratio": "anyres_max_9",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 26,
    "patch_size": 14,
    "vision_use_head": false
  },
  "vision_feature_layer": -1,
  "vision_feature_select_strategy": "full"
}