config.json

{
  "_name_or_path": "Qwen/Qwen2-7B-Instruct",
  "architectures": [
    "RossQwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "decode_image_size": 432,
  "eos_token_id": 151645,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "image_aspect_ratio": "pad",
  "image_embed_len": 729,
  "image_mean": [
    0.5,
    0.5,
    0.5
  ],
  "image_std": [
    0.5,
    0.5,
    0.5
  ],
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "mm_hidden_size": 1152,
  "mm_inv_hidden_size": 64,
  "mm_inv_projector_lr": null,
  "mm_inv_projector_type": "denoiser_vit3x",
  "mm_patch_merge_type": "flat",
  "mm_pixel_decoder": "./pretrained_vae",
  "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": "google/siglip-so400m-patch14-384",
  "mm_vision_tower_lr": 2e-06,
  "model_type": "ross_qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "pad_token_id": 151643,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "ross_enable": true,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 4096,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.1",
  "tune_mm_mlp_adapter": false,
  "unfreeze_mm_vision_tower": false,
  "use_cache": true,
  "use_mm_inv_proj": true,
  "use_mm_proj": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}