config.json

{
  "_name_or_path": "../../groma-7b-finetune",
  "architectures": [
    "GromaModel"
  ],
  "box_score_thres": 0.15,
  "llm_cfg": {
    "_name_or_path": "vicuna-7b-v1.5",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "max_position_embeddings": 4096,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 32,
    "pad_token_id": 0,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float16",
    "transformers_version": "4.39.3",
    "use_cache": true,
    "vocab_size": 32000
  },
  "max_region_num": 100,
  "model_type": "groma",
  "nms_thres": 0.6,
  "num_new_token": 114,
  "perceiver_cfg": {
    "architectures": [
      "CustomDDETRModel"
    ],
    "ddetr_cfg": {
      "auxiliary_loss": true,
      "class_cost": 2,
      "cls_loss_coefficient": 2,
      "id2label": {
        "0": "LABEL_0"
      },
      "label2id": {
        "LABEL_0": 0
      },
      "model_type": "deformable_detr",
      "num_feature_levels": 1,
      "two_stage": true,
      "with_box_refine": true
    },
    "model_type": "ddetr",
    "torch_dtype": "float32",
    "transformers_version": "4.39.3",
    "vis_encoder_cfg": {
      "architectures": [
        "Dinov2Model"
      ],
      "hidden_size": 1024,
      "image_size": 518,
      "model_type": "dinov2",
      "num_attention_heads": 16,
      "num_hidden_layers": 24,
      "out_features": [
        "stage24"
      ],
      "out_indices": [
        24
      ],
      "patch_size": 14,
      "stage_names": [
        "stem",
        "stage1",
        "stage2",
        "stage3",
        "stage4",
        "stage5",
        "stage6",
        "stage7",
        "stage8",
        "stage9",
        "stage10",
        "stage11",
        "stage12",
        "stage13",
        "stage14",
        "stage15",
        "stage16",
        "stage17",
        "stage18",
        "stage19",
        "stage20",
        "stage21",
        "stage22",
        "stage23",
        "stage24"
      ],
      "torch_dtype": "float32"
    },
    "vis_output_layer": -2,
    "zs_weight_path": null
  },
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "fp4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.39.3",
  "vocab_size": 32114
}