CoolFace
Modelpublic

HashNuke/pp-doclayout-v3-mlx

sourceHugging Faceapache-2.0updated 14d agoView on Hugging Face
0likes56downloads
config.json108 linesDownload Raw Back to root
1{2  "activation_dropout": 0.0,3  "activation_function": "silu",4  "anchor_image_size": null,5  "architectures": [6    "PPDocLayoutV3ForObjectDetection"7  ],8  "attention_dropout": 0.0,9  "backbone": null,10  "backbone_config": {11    "model_type": "hgnet_v2",12    "arch": "L",13    "return_idx": [0, 1, 2, 3],14    "freeze_stem_only": true,15    "freeze_at": 0,16    "freeze_norm": true,17    "lr_mult_list": [0, 0.05, 0.05, 0.05, 0.05],18    "out_features": ["stage1", "stage2", "stage3", "stage4"]19  },20  "backbone_kwargs": null,21  "batch_norm_eps": 1e-05,22  "box_noise_scale": 1.0,23  "d_model": 256,24  "decoder_activation_function": "relu",25  "decoder_attention_heads": 8,26  "decoder_ffn_dim": 1024,27  "decoder_in_channels": [28    256,29    256,30    25631  ],32  "decoder_layers": 6,33  "decoder_n_points": 4,34  "disable_custom_kernels": true,35  "dropout": 0.0,36  "encode_proj_layers": [37    238  ],39  "encoder_activation_function": "gelu",40  "encoder_attention_heads": 8,41  "encoder_ffn_dim": 1024,42  "encoder_hidden_dim": 256,43  "encoder_in_channels": [44    512,45    1024,46    204847  ],48  "encoder_layers": 1,49  "eos_coefficient": 0.0001,50  "eval_size": null,51  "feature_strides": [52    8,53    16,54    3255  ],56  "hidden_expansion": 1.0,57  "id2label": {58    "0": "abstract",59    "1": "algorithm",60    "2": "aside_text",61    "3": "chart",62    "4": "content",63    "5": "formula",64    "6": "doc_title",65    "7": "figure_title",66    "8": "footer",67    "9": "footer",68    "10": "footnote",69    "11": "formula_number",70    "12": "header",71    "13": "header",72    "14": "image",73    "15": "formula",74    "16": "number",75    "17": "paragraph_title",76    "18": "reference",77    "19": "reference_content",78    "20": "seal",79    "21": "table",80    "22": "text",81    "23": "text",82    "24": "vision_footnote"83  },84  "initializer_range": 0.01,85  "is_encoder_decoder": true,86  "label2id": {},87  "label_noise_ratio": 0.5,88  "layer_norm_eps": 1e-05,89  "learn_initial_query": false,90  "matcher_alpha": 0.25,91  "matcher_bbox_cost": 5.0,92  "matcher_class_cost": 2.0,93  "matcher_gamma": 2.0,94  "matcher_giou_cost": 2.0,95  "model_type": "pp_doclayout_v3",96  "normalize_before": false,97  "num_denoising": 100,98  "num_feature_levels": 3,99  "num_queries": 300,100  "positional_encoding_temperature": 10000,101  "torch_dtype": "float32",102  "use_pretrained_backbone": false,103  "use_timm_backbone": false,104  "global_pointer_head_size": 64,105  "mask_feature_channels": [64, 64],106  "x4_feat_dim": 128107}108