config.json

{
  "_name_or_path": "Xenova/tiny-random-LlavaForConditionalGeneration",
  "architectures": [
    "LlavaForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_token_index": 32000,
  "model_type": "llava",
  "projector_hidden_act": "gelu",
  "text_config": {
    "architectures": [
      "PhiForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "embd_pdrop": 0.0,
    "eos_token_id": 1,
    "hidden_act": "silu",
    "hidden_size": 16,
    "initializer_range": 0.02,
    "intermediate_size": 64,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 2048,
    "model_type": "phi",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "num_key_value_heads": 4,
    "pad_token_id": -1,
    "partial_rotary_factor": 0.5,
    "pretraining_tp": 1,
    "qk_layernorm": false,
    "resid_pdrop": 0.0,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float32",
    "transformers_version": "4.38.2",
    "use_cache": true,
    "vocab_size": 32002
  },
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "vision_config": {
    "attention_dropout": 0.1,
    "dropout": 0.1,
    "hidden_size": 32,
    "image_size": 30,
    "intermediate_size": 37,
    "model_type": "clip_vision_model",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "patch_size": 2,
    "projection_dim": 32
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default",
  "vocab_size": 32002
}