config.json

{
  "architectures": [
    "TinyEmoForConditionalGeneration"
  ],
  "cache_dir": null,
  "connector_type": "mlp2x_gelu",
  "hidden_size": 2560,
  "ignore_index": -100,
  "image_aspect_ratio": "square",
  "image_token_index": -200,
  "llm_model_name_or_path": "microsoft/phi-2",
  "model_type": "tinyemo",
  "num_queries": 128,
  "num_resampler_layers": 3,
  "pad_token": "<|endoftext|>",
  "pad_token_id": 50256,
  "resampler_hidden_size": 768,
  "text_config": {
    "_name_or_path": "microsoft/phi-2",
    "architectures": [
      "PhiForCausalLM"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 50256,
    "embd_pdrop": 0.0,
    "eos_token_id": 50256,
    "hidden_act": "gelu_new",
    "hidden_size": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 10240,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 2048,
    "model_type": "phi",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 32,
    "partial_rotary_factor": 0.4,
    "qk_layernorm": false,
    "resid_pdrop": 0.1,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.37.0",
    "use_cache": true,
    "vocab_size": 51200
  },
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "tokenizer_use_fast": false,
  "torch_dtype": "float16",
  "transformers_version": "4.37.0",
  "tune_type_connector": "full",
  "tune_type_llm": "full",
  "tune_type_vision_tower": "frozen",
  "tune_vision_tower_from_layer": 0,
  "use_cache": true,
  "vision_config": {
    "_name_or_path": "openai/clip-vit-large-patch14",
    "architectures": [
      "CLIPModel"
    ],
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 224,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "patch",
  "vision_hidden_size": 1024,
  "vision_model_name_or_path": "openai/clip-vit-large-patch14",
  "vocab_size": 51200
}