Upload folder using huggingface_hub

README.md

@@ -0,0 +1,32 @@
+---
+language:
+- en
+- zh
+tags:
+- mlx
+- object-detection
+- document-layout
+library_name: mlx-vlm
+---
+
+# pp-doclayout-v3-mlx
+
+MLX port of [PaddlePaddle/PP-DocLayoutV3_safetensors](https://huggingface.co/PaddlePaddle/PP-DocLayoutV3_safetensors):
+RT-DETR-style document layout detector, 25 classes plus a reading-order
+head (33M params, float32).
+
+```python
+from mlx_vlm.utils import load_model
+
+model = load_model("HashNuke/pp-doclayout-v3-mlx")
+model.eval()
+print(model.detect("page.png", conf=0.5))
+```
+
+Also usable as the layout backend for Falcon-OCR style pipelines, and
+the architecture twin of the 37-class IndicDocLayout fine-tune
+(`HashNuke/indic-ocr-mlx` `weights/layout`).
+
+Original weights: Apache-2.0. Port code:
+`mlx_vlm/models/pp_doclayout_v3` in mlx-vlm. Converted with
+`python -m mlx_vlm.models.pp_doclayout_v3.convert --dtype float32`.

config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "anchor_image_size": null,
+  "architectures": [
+    "PPDocLayoutV3ForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "backbone": null,
+  "backbone_config": {
+    "model_type": "hgnet_v2",
+    "arch": "L",
+    "return_idx": [0, 1, 2, 3],
+    "freeze_stem_only": true,
+    "freeze_at": 0,
+    "freeze_norm": true,
+    "lr_mult_list": [0, 0.05, 0.05, 0.05, 0.05],
+    "out_features": ["stage1", "stage2", "stage3", "stage4"]
+  },
+  "backbone_kwargs": null,
+  "batch_norm_eps": 1e-05,
+  "box_noise_scale": 1.0,
+  "d_model": 256,
+  "decoder_activation_function": "relu",
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 1024,
+  "decoder_in_channels": [
+    256,
+    256,
+    256
+  ],
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "disable_custom_kernels": true,
+  "dropout": 0.0,
+  "encode_proj_layers": [
+    2
+  ],
+  "encoder_activation_function": "gelu",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 1024,
+  "encoder_hidden_dim": 256,
+  "encoder_in_channels": [
+    512,
+    1024,
+    2048
+  ],
+  "encoder_layers": 1,
+  "eos_coefficient": 0.0001,
+  "eval_size": null,
+  "feature_strides": [
+    8,
+    16,
+    32
+  ],
+  "hidden_expansion": 1.0,
+  "id2label": {
+    "0": "abstract",
+    "1": "algorithm",
+    "2": "aside_text",
+    "3": "chart",
+    "4": "content",
+    "5": "formula",
+    "6": "doc_title",
+    "7": "figure_title",
+    "8": "footer",
+    "9": "footer",
+    "10": "footnote",
+    "11": "formula_number",
+    "12": "header",
+    "13": "header",
+    "14": "image",
+    "15": "formula",
+    "16": "number",
+    "17": "paragraph_title",
+    "18": "reference",
+    "19": "reference_content",
+    "20": "seal",
+    "21": "table",
+    "22": "text",
+    "23": "text",
+    "24": "vision_footnote"
+  },
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {},
+  "label_noise_ratio": 0.5,
+  "layer_norm_eps": 1e-05,
+  "learn_initial_query": false,
+  "matcher_alpha": 0.25,
+  "matcher_bbox_cost": 5.0,
+  "matcher_class_cost": 2.0,
+  "matcher_gamma": 2.0,
+  "matcher_giou_cost": 2.0,
+  "model_type": "pp_doclayout_v3",
+  "normalize_before": false,
+  "num_denoising": 100,
+  "num_feature_levels": 3,
+  "num_queries": 300,
+  "positional_encoding_temperature": 10000,
+  "torch_dtype": "float32",
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false,
+  "global_pointer_head_size": 64,
+  "mask_feature_channels": [64, 64],
+  "x4_feat_dim": 128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57d0def397166f9518572b7a01472e2d23c14de0455f1b82fae465a78ca6d9e5
+size 133232741