{
  "_name_or_path": "TinyLLaVA-1.5B",
  "architectures": [
    "TinyLlavaLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "image_aspect_ratio": "pad",
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 2048,
  "mm_hidden_size": 1152,
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "bczhou/TinyLLaVA-1.5B-SigLIP",
  "model_type": "tiny_llava",
  "num_attention_heads": 32,
  "num_hidden_layers": 22,
  "num_key_value_heads": 4,
  "pad_token": "<unk>",
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float16",
  "transformers_version": "4.37.2",
  "tune_embed_tokens": false,
  "tune_entire_model": false,
  "tune_mm_mlp_adapter": false,
  "tune_vision_tower": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 32000
}