Duplicate from microsoft/layoutlmv2-base-uncased

Co-authored-by: Julien Chaumond <julien-c@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,16 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,17 @@
+---
+language: en
+license: cc-by-nc-sa-4.0
+
+---
+
+# LayoutLMv2
+**Multimodal (text + layout/format + image) pre-training for document AI**
+
+The documentation of this model in the Transformers library can be found [here](https://huggingface.co/docs/transformers/model_doc/layoutlmv2).
+
+[Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/) | [GitHub](https://github.com/microsoft/unilm/tree/master/layoutlmv2)
+## Introduction
+LayoutLMv2 is an improved version of LayoutLM with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. It outperforms strong baselines and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including , including FUNSD (0.7895 → 0.8420), CORD (0.9493 → 0.9601), SROIE (0.9524 → 0.9781), Kleister-NDA (0.834 → 0.852), RVL-CDIP (0.9443 → 0.9564), and DocVQA (0.7295 → 0.8672).
+
+[LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://arxiv.org/abs/2012.14740)
+Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou, ACL 2021

config.json

@@ -0,0 +1,31 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "coordinate_size": 128,
+  "fast_qkv": true,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "image_feature_pool_shape": [
+    7,
+    7,
+    256
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 512,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "shape_size": 128,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

preprocessor_config.json

@@ -0,0 +1,7 @@
+{
+  "apply_ocr": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv2FeatureExtractor",
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cffd5ed065ff81e1e5c9a38968372c8541ecb8499999c89a8d9e10d65de3406
+size 802243295