config.json

{
  "_name_or_path": "/mnt/bn/vl-research/checkpoints/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen1.5-7B-Chat-mlp2x_gelu-finetune_la1_6mix_fvis_direct32k_anyres_check_toml_trial6",
  "architectures": [
    "LlavaQwenForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "anyres",
  "image_crop_resolution": 224,
  "image_grid_pinpoints": [
    [
      384,
      768
    ],
    [
      768,
      384
    ],
    [
      768,
      768
    ],
    [
      1152,
      384
    ],
    [
      384,
      1152
    ]
  ],
  "image_split_resolution": 224,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "mm_hidden_size": 1152,
  "mm_patch_merge_type": "spatial_unpad",
  "mm_projector_lr": null,
  "mm_projector_type": "mlp2x_gelu",
  "mm_resampler_type": null,
  "mm_tunable_parts": "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": -2,
  "mm_vision_tower": "google/siglip-so400m-patch14-384",
  "mm_vision_tower_lr": null,
  "model_type": "llava_qwen",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": 32768,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 32768,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.39.0.dev0",
  "use_cache": true,
  "use_mm_proj": true,
  "use_sliding_window": false,
  "vision_tower_pretrained": null,
  "vocab_size": 151936
}