config.json

{
  "architectures": [
    "NVILAForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_nvila.NVILAConfig",
    "AutoModel": "modeling_nvila.NVILAForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_nvila.NVILAForConditionalGeneration",
    "AutoModelForImageTextToText": "modeling_nvila.NVILAForConditionalGeneration",
    "AutoModelForVision2Seq": "modeling_nvila.NVILAForConditionalGeneration"
  },
  "image_token_id": 151649,
  "model_type": "nvila",
  "text_config": {
    "_attn_implementation_autoset": false,
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "hidden_act": "silu",
    "hidden_size": 3584,
    "initializer_range": 0.02,
    "intermediate_size": 18944,
    "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"
    ],
    "max_position_embeddings": 32768,
    "max_window_layers": 28,
    "model_max_length": 8192,
    "model_type": "qwen2",
    "num_attention_heads": 28,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": null,
    "tokenizer_model_max_length": 8192,
    "tokenizer_padding_side": "right",
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151651
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.55.4",
  "video_token_id": 151650,
  "vision_config": {
    "_attn_implementation_autoset": false,
    "architectures": [
      "SiglipVisionModel"
    ],
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 448,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "num_image_tokens": 256,
    "patch_size": 14,
    "projection_dim": 2048,
    "projector_hidden_act": "gelu_fast",
    "torch_dtype": "bfloat16",
    "vision_use_head": false
  }
}