config.json

{
  "architectures": [
    "TinyDocVLMForConditionalGeneration"
  ],
  "decoder_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "head_dim": 64,
    "hidden_act": "silu",
    "hidden_size": 576,
    "initializer_range": 0.02,
    "intermediate_size": 1536,
    "max_position_embeddings": 8192,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 9,
    "num_hidden_layers": 30,
    "num_key_value_heads": 3,
    "pad_token_id": null,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-06,
    "rope_parameters": {
      "rope_theta": 273000.0,
      "rope_type": "default"
    },
    "tie_word_embeddings": false,
    "use_cache": true,
    "vocab_size": 49184
  },
  "dtype": "float32",
  "image_size": 384,
  "model_type": "tinydoc_vlm",
  "patch_size": 16,
  "pixel_shuffle_scale": 3,
  "transformers_version": "5.10.2",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "image_size": 384,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16
  }
}