first commit

README.md

@@ -1,3 +1,33 @@
-# layoutlmv3-large_a13684308344434688439059
+---
+language: en
+license: cc-by-nc-sa-4.0
 
-layoutlmv3-large
+---
+# LayoutLMv3
+
+[Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://aka.ms/layoutlmv3)
+
+## Model description
+
+LayoutLMv3 is a pre-trained multimodal Transformer for Document AI with unified text and image masking. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model. For example, LayoutLMv3 can be fine-tuned for both text-centric tasks, including form understanding, receipt understanding, and document visual question answering, and image-centric tasks such as document image classification and document layout analysis.
+
+[LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://arxiv.org/abs/2204.08387)
+Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, Furu Wei, Preprint 2022.
+
+## Citation
+
+If you find LayoutLM useful in your research, please cite the following paper:
+```
+@inproceedings{huang2022layoutlmv3,
+  author={Yupan Huang and Tengchao Lv and Lei Cui and Yutong Lu and Furu Wei},
+  title={LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking},
+  booktitle={Proceedings of the 30th ACM International Conference on Multimedia},
+  year={2022}
+}
+```
+
+## License
+
+The content of this project itself is licensed under the [Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/).
+Portions of the source code are based on the [transformers](https://github.com/huggingface/transformers) project.
+[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct)

config.json

@@ -0,0 +1,33 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "coordinate_size": 171,
+  "eos_token_id": 2,
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "second_input_size": 112,
+  "shape_size": 170,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "apply_ocr": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ocr_lang": null,
+  "resample": 2,
+  "size": 224
+}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "roberta-large", "tokenizer_class": "LayoutLMv3Tokenizer"}