config.json

{
  "_name_or_path": "microsoft/Phi-3-vision-128k-instruct",
  "architectures": [
    "Phi3VForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "microsoft/Phi-3-vision-128k-instruct--configuration_phi3_v.Phi3VConfig",
    "AutoModelForCausalLM": "microsoft/Phi-3-vision-128k-instruct--modeling_phi3_v.Phi3VForCausalLM"
  },
  "bos_token_id": 1,
  "embd_layer": {
    "embedding_cls": "image",
    "hd_transform_order": "sub_glb",
    "projection_cls": "mlp",
    "use_hd_transform": true,
    "with_learnable_separator": true
  },
  "embd_pdrop": 0.0,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 16,
  "img_processor": {
    "image_dim_out": 1024,
    "model_name": "openai/clip-vit-large-patch14-336",
    "name": "clip_vision_model",
    "num_img_tokens": 144
  },
  "initializer_range": 0.02,
  "intermediate_size": 32,
  "max_position_embeddings": 131072,
  "model_type": "phi3_v",
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "num_key_value_heads": 4,
  "original_max_position_embeddings": 4096,
  "pad_token_id": 32000,
  "resid_pdrop": 0.0,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "long_factor": [
      1.0299,
      1.0499
    ],
    "short_factor": [
      1.05,
      1.05
    ],
    "type": "su"
  },
  "rope_theta": 10000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.42.1",
  "use_cache": true,
  "vocab_size": 32064
}