{
  "_name_or_path": "/mnt/bn/vl-research/workspace/yhzhang/llava-video-old/work_dirs/llava-Yi_34B-mlp2x_gelu-pretrain_blip558k_plain-336px-ft-video_image_mix-frames_upbound_32-pool_stride_2-model_max_length_8192",
  "architectures": [
    "LlavaLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 7,
  "freeze_mm_mlp_adapter": true,
  "freeze_mm_vision_resampler": false,
  "hidden_act": "silu",
  "hidden_size": 7168,
  "image_aspect_ratio": "anyres",
  "image_crop_resolution": 224,
  "image_grid_pinpoints": [
    [
      336,
      672
    ],
    [
      672,
      336
    ],
    [
      672,
      672
    ],
    [
      1008,
      336
    ],
    [
      336,
      1008
    ]
  ],
  "image_split_resolution": 224,
  "initializer_range": 0.02,
  "intermediate_size": 20480,
  "max_position_embeddings": 4096,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "spatial_unpad",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": "spatial_pool",
  "mm_spatial_pool_mode": "average",
  "mm_spatial_pool_out_channels": 1024,
  "mm_spatial_pool_stride": 2,
  "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": "openai/clip-vit-large-patch14-336",
  "mm_vision_tower_lr": null,
  "model_type": "llava_llama",
  "num_attention_heads": 56,
  "num_hidden_layers": 60,
  "num_key_value_heads": 8,
  "pad_token_id": 0,
  "patchify_video_feature": false,
  "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": "4.39.2",
  "tune_mm_mlp_adapter": false,
  "tune_mm_vision_resampler": false,
  "unfreeze_mm_vision_tower": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 64000
}