config.json

{
  "_name_or_path": "../llava-v1.5-7b-2",
  "architectures": [
    "LlavaLlamaForCausalLM"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "extra": {
    "highres_size": "1008",
    "lowres_size": "336",
    "threshold": "48",
    "warmup": "10",
    "zoom_ratio": "3"
  },
  "freeze_mm_mlp_adapter": false,
  "freeze_mm_vision_resampler": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "ignore_index": -100,
  "image_aspect_ratio": "pad",
  "image_token_index": 32000,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_length": 4096,
  "max_position_embeddings": 4096,
  "mm_hidden_size": 1024,
  "mm_patch_merge_type": "flat",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "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",
  "model_type": "llava",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "projector_hidden_act": "gelu",
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "text_config": {
    "model_type": "llama"
  },
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 2048,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float16",
  "transformers_version": "4.37.2",
  "tune_mm_mlp_adapter": false,
  "tune_mm_vision_resampler": false,
  "unfreeze_mm_vision_tower": false,
  "use_cache": false,
  "use_mm_proj": true,
  "vision_config": {
    "hidden_size": 1024,
    "image_size": 336,
    "intermediate_size": 4096,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768,
    "vocab_size": 32000
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default",
  "vocab_size": 32000
}