config.json

{
  "_name_or_path": "/group/40079/yinanzhou/LLaVA-NeXT/checkpoints/high/llavanext-model_zoo_InternViT-300M-448px-from-InternVL2-8b-model_zoo_Qwen_Qwen2-7B-Instruct-ln_mlp2x_gelu-mplug-PCG-full5M-pretrain-decode_correct-no-padding-48npu--qwen_1_5",
  "architectures": [
    "LlavaQwenForCausalLM"
  ],
  "attention_dropout": 0.0,
  "best_resolution_select_mode": "nearest_no_padding",
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_aspect_ratio": "anyres_max_9",
  "image_crop_resolution": null,
  "image_grid_pinpoints": "16",
  "image_split_resolution": null,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "mm_hidden_size": 4096,
  "mm_newline_position": "one_token",
  "mm_patch_merge_type": "linebreak",
  "mm_projector_lr": null,
  "mm_projector_type": "ln_mlp2x_gelu",
  "mm_resampler_type": null,
  "mm_spatial_pool_mode": "bilinear",
  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -1,
  "mm_vision_tower": "model_zoo/InternViT-300M-448px-from-InternVL2-8b",
  "mm_vision_tower_lr": 2e-06,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "pos_skipping_range": 4096,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 6144,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_mm_proj": true,
  "use_pos_skipping": false,
  "use_sliding_window": false,
  "vision_tower_pretrained": null,
  "vocab_size": 152064
}