{
  "activation_function": "gelu_new",
  "architectures": [
    "LlavaGPTForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_pdrop": 0.1,
  "bos_token_id": 1,
  "detect_loss": false,
  "embd_pdrop": 0.1,
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "image_aspect_ratio": "pad",
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "is_decoder": true,
  "layer_norm_epsilon": 1e-05,
  "mm_projector_lr": null,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_tower": "dino",
  "model_type": "gpt2",
  "n_embd": 768,
  "n_head": 12,
  "n_inner": null,
  "n_layer": 12,
  "n_positions": 1024,
  "num_key_value_heads": 12,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "tie_word_embeddings": false,
  "tokenizer_class": "LlamaTokenizer",
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float32",
  "transformers_version": "4.38.0",
  "tune_mm_mlp_adapter": false,
  "use_cache": false,
  "vision_tower_type": "dino",
  "vocab_size": 25005
}