Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+Here's how the README file for your `surya-ocr-arabic` model could look:
+
+---
+
+# Surya OCR Arabic
+
+This repository contains the `surya-ocr-arabic` model, which is based on a modified SegFormer architecture. The model was fine-tuned for document layout detection tasks.
+
+
+## Setup Instructions
+
+### Clone the Surya OCR GitHub Repository
+
+To use the `SegformerForRegressionMask` class, you need to clone the Surya OCR GitHub repository:
+
+```bash
+git clone https://github.com/vikp/surya_.git
+cd surya
+```
+
+### Switch to v0.4.14
+
+```bash
+git checkout f7c6c04
+```
+
+### Install Dependencies
+
+You can install the required dependencies using the following command:
+
+```bash
+pip install -r requirements.txt
+```
+
+### Import and Use the Model
+
+You can load and use the `surya-ocr-arabic` model as follows:
+
+```python
+from surya.surya.model.detection.segformer import SegformerForRegressionMask
+import torch
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model = SegformerForRegressionMask.from_pretrained("ketanmore/surya-ocr-arabic-segment", torch_dtype=torch.float32).to(device)
+```

config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "vikp/surya_det2",
+  "architectures": [
+    "SegformerForRegressionMask"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 768,
+  "decoder_layer_hidden_size": 192,
+  "decoder_upsample_rate": 2,
+  "depths": [
+    3,
+    4,
+    9,
+    3
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "id2label": {
+    "0": "blank",
+    "1": "text"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "blank": 0,
+    "text": 1
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": -1,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0ea4e8d36542029f2398ee982cfca61aa43a8ada62f64a099868aa0d157ef35
+size 119881240