{
  "_name_or_path": "Mini-Gemini-34B-HD",
  "architectures": [
    "MiniGeminiLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "aux_img_fold": false,
  "aux_with_fpn": false,
  "bos_token_id": 1,
  "eos_token_id": 7,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 7168,
  "image_aspect_ratio": "pad",
  "image_global": true,
  "image_grid": 2,
  "image_grid_pinpoints": null,
  "image_size_aux": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 20480,
  "max_position_embeddings": 4096,
  "mm_hidden_size": 1024,
  "mm_hidden_size_aux": 2880,
  "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": "model_zoo/OpenAI/clip-vit-large-patch14-336",
  "mm_vision_tower_aux": "model_zoo/OpenAI/openclip-convnext-large-d-320-laion2B-s29B-b131K-ft-soup",
  "model_type": "mini_gemini",
  "num_attention_heads": 56,
  "num_hidden_layers": 60,
  "num_key_value_heads": 8,
  "optimize_vision_tower": false,
  "optimize_vision_tower_aux": false,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 5000000.0,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 4096,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.36.2",
  "tune_mm_mlp_adapter": false,
  "use_cache": false,
  "use_mm_proj": true,
  "video_grid": -1,
  "vocab_size": 64000
}