config.json

{
  "_name_or_path": "",
  "aligner_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cls": "MlpProjector",
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "aligner",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "params": {
      "depth": 2,
      "input_dim": 1024,
      "n_embed": 3584,
      "projector_type": "low_high_hybrid_split_mlp_gelu"
    },
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "architectures": [
    "UrsaForTokenClassification"
  ],
  "ignore_index": -100,
  "image_token_index": 151665,
  "model_type": "ursa",
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "",
    "architectures": [
      "Qwen2ForCausalLM"
    ],
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "hidden_size": 3584,
    "intermediate_size": 18944,
    "max_position_embeddings": 4096,
    "max_window_layers": 28,
    "model_type": "qwen2",
    "num_attention_heads": 28,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "sliding_window": null,
    "torch_dtype": "bfloat16",
    "use_sliding_window": false,
    "vocab_size": 151668
  },
  "torch_dtype": "float32",
  "transformers_version": "4.45.1",
  "vision_config": {
    "cls": "HybridVisionTower",
    "model_type": "vision",
    "params": {
      "concat_type": "tuple",
      "freeze_high": true,
      "freeze_low": true,
      "high_res_cfg": {
        "ckpt_path": "",
        "image_size": 1024,
        "model_name": "sam_b_downsample",
        "output_dim": 1024,
        "pixel_mean": [
          0.48145466,
          0.4578275,
          0.40821073
        ],
        "pixel_std": [
          0.26862954,
          0.26130258,
          0.27577711
        ],
        "select_feature": "same",
        "select_layer": -1
      },
      "low_res_cfg": {
        "ckpt_path": "",
        "image_size": 384,
        "model_name": "siglip_large_patch16_384",
        "output_dim": 1024,
        "pixel_mean": [
          0.5,
          0.5,
          0.5
        ],
        "pixel_std": [
          0.5,
          0.5,
          0.5
        ],
        "select_feature": "same",
        "select_layer": -1
      }
    }
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}