First Model Version

README.md

@@ -1,3 +1,28 @@
 ---
 license: cc-by-nc-4.0
 ---
+
+# TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
+<p align="center">
+    <img src="assets/framework.png" width="800">
+</p>
+
+<p align="center">
+     📃 <a href="https://arxiv.org/pdf/2406.01326" target="_blank">Paper</a> | 🤗 <a href="https://huggingface.co/datasets/ByteDance/ComTQA" target="_blank">Hugging Face</a> | 🚀 <a href="https://github.com/zhaowc-ustc/TabPedia-Towards-Comprehensive-Visual-Table-Understanding-with-Concept-Synergy" target="_blank">Github</a>
+
+</p>
+
+This repository includes our pretrained model and dount model for better evaluation.
+
+
+## Citation
+
+If you find this work useful, please consider citing our paper:
+```
+@article{zhao2024tabpedia,
+title={TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy},
+author={Zhao, Weichao and Feng, Hao and Liu, Qi and Tang, Jingqun and Wei, Shu and Wu, Binghong and Liao, Lei and Ye, Yongjie and Liu, Hao and Li, Houqiang and others},
+journal={arXiv preprint arXiv:2406.01326},
+year={2024}
+}
+```

TabPedia/pretrained.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:595cfa0e019b40f2bf9080db78a0ca820f940aa71f407f31b0fc1e20216a0980
+size 31634109147

donut-base/README.md

@@ -0,0 +1,3 @@
+---
+license: mit
+---

donut-base/added_tokens.json

@@ -0,0 +1 @@
+{"<sep/>": 57522, "<s_iitcdip>": 57523, "<s_synthdog>": 57524}

donut-base/config.json

@@ -0,0 +1,23 @@
+{
+  "align_long_axis": true,
+  "architectures": [
+    "DonutModel"
+  ],
+  "decoder_layer": 4,
+  "encoder_layer": [
+    2,
+    2,
+    14,
+    2
+  ],
+  "input_size": [
+    2560,
+    1920
+  ],
+  "max_length": 1536,
+  "max_position_embeddings": 1536,
+  "model_type": "donut",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "window_size": 10
+}

donut-base/gitattributes.txt

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

donut-base/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21e8b5e708168f4f9885d18f8bc95ad6950439e7ac518161828ff0b27b984e8
+size 1018458179

donut-base/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

donut-base/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<s_iitcdip>", "<s_synthdog>"]}

donut-base/tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/213c2041358e63047b407f94cde1ae23904d31a3bceb57eab291028c1e949437.7135a4b25ac726e19641f0d68803ff02bad960d6319064f55fa9c536929b86fc", "name_or_path": "hyunwoongko/asian-bart-ecjk", "tokenizer_class": "XLMRobertaTokenizer"}