config.json

{
  "architectures": [
    "AnyResVisionLanguageModel"
  ],
  "language_model_config": {
    "architectures": [
      "MistralForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 32768,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_theta": 1000000.0,
    "sliding_window": null,
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 32064
  },
  "model_type": "anyres_vision_language_model",
  "projector_config": {
    "hidden_act": "gelu",
    "in_features": 1024,
    "model_type": "llava_next_projector",
    "out_features": 4096
  },
  "torch_dtype": "float16",
  "transformers_version": "4.40.0.dev0",
  "vision_tower_config": {
    "model_type": "clip_vision_tower",
    "pretrained_model_name_or_path": "openai/clip-vit-large-patch14-336",
    "select_feature": "patch",
    "select_layer": -2
  }
}