config.json

{
    "_name_or_path": "DeepGlint-AI/MLCD-Seg",
    "add_faster_video": false,
    "add_time_instruction": false,
    "architectures": [
      "MLCDSegForCausalLM"
    ],
    "auto_map": {
        "AutoConfig": "mlcd_seg.MLCDSegConfig",
        "AutoModel": "mlcd_seg.MLCDSegForCausalLM",
        "AutoModelForCausalLM": "mlcd_seg.MLCDSegForCausalLM"
    },
    "attn_implementation": "flash_attention_2",
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "faster_token_stride": 10,
    "force_sample": false,
    "hidden_act": "silu",
    "hidden_size": 3584,
    "image_aspect_ratio": "anyres",
    "image_crop_resolution": null,
    "image_grid_pinpoints": [
      [
        336,
        336
      ],
      [
        336,
        672
      ],
      [
        336,
        1008
      ],
      [
        336,
        1344
      ],
      [
        336,
        1680
      ],
      [
        336,
        2016
      ],
      [
        672,
        336
      ],
      [
        672,
        672
      ],
      [
        672,
        1008
      ],
      [
        672,
        1344
      ],
      [
        672,
        1680
      ],
      [
        672,
        2016
      ],
      [
        1008,
        336
      ],
      [
        1008,
        672
      ],
      [
        1008,
        1008
      ],
      [
        1008,
        1344
      ],
      [
        1008,
        1680
      ],
      [
        1008,
        2016
      ],
      [
        1344,
        336
      ],
      [
        1344,
        672
      ],
      [
        1344,
        1008
      ],
      [
        1344,
        1344
      ],
      [
        1344,
        1680
      ],
      [
        1344,
        2016
      ],
      [
        1680,
        336
      ],
      [
        1680,
        672
      ],
      [
        1680,
        1008
      ],
      [
        1680,
        1344
      ],
      [
        1680,
        1680
      ],
      [
        1680,
        2016
      ],
      [
        2016,
        336
      ],
      [
        2016,
        672
      ],
      [
        2016,
        1008
      ],
      [
        2016,
        1344
      ],
      [
        2016,
        1680
      ],
      [
        2016,
        2016
      ]
    ],
    "image_split_resolution": null,
    "initializer_range": 0.02,
    "intermediate_size": 18944,
    "max_position_embeddings": 32768,
    "max_window_layers": 28,
    "mm_hidden_size": 1024,
    "mm_newline_position": "grid",
    "mm_patch_merge_type": "spatial_unpad",
    "mm_projector_lr": null,
    "mm_projector_type": "mlp2x_gelu",
    "mm_resampler_type": null,
    "mm_spatial_pool_mode": "bilinear",
    "mm_spatial_pool_stride": null,
    "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model,sam",
    "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_lr": 2e-06,
    "vision_tower_config": {
        "_name_or_path": "",
        "architectures": [ 
            "CLIPVisionModel" 
        ], 
        "attention_dropout": 0.0, 
        "hidden_act": "quick_gelu", 
        "hidden_size": 1024, 
        "image_size": 336, 
        "initializer_factor": 1.0, 
        "initializer_range": 0.02, 
        "intermediate_size": 4096, 
        "layer_norm_eps": 1e-05, 
        "model_type": "clip_vision_model", 
        "num_attention_heads": 16, 
        "num_channels": 3, 
        "num_hidden_layers": 24, 
        "patch_size": 14, 
        "projection_dim": 1024, 
        "torch_dtype": "float32", 
        "transformers_version": "4.44.0"
    },
    "vision_tower_processor": {
        "crop_size": 336,
        "do_center_crop": true,
        "do_normalize": true,
        "do_resize": true,
        "feature_extractor_type": "CLIPFeatureExtractor",
        "image_mean": [
          0.48145466,
          0.4578275,
          0.40821073
        ],
        "image_std": [
          0.26862954,
          0.26130258,
          0.27577711
        ],
        "resample": 3,
        "size": 336
    },
    "model_type": "qwen2",
    "num_attention_heads": 28,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "pos_skipping_range": 4096,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": null,
    "tie_word_embeddings": false,
    "tokenizer_model_max_length": 32768,
    "tokenizer_padding_side": "right",
    "torch_dtype": "bfloat16",
    "transformers_version": "4.47.0",
    "use_cache": true,
    "use_mm_proj": true,
    "use_pos_skipping": false,
    "use_sliding_window": false,
    "vision_tower_pretrained": null,
    "vocab_size": 151666
  }