Yiheng Xu commited on
Commit
f6781a3
1 Parent(s): 87c0fb9
Files changed (4) hide show
  1. README.md +8 -0
  2. config.json +35 -0
  3. pytorch_model.bin +3 -0
  4. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ # LayoutLMv2
2
+ **Multimodal (text + layout/format + image) pre-training for document AI**
3
+
4
+ ## Introduction
5
+ 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).
6
+
7
+ [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://arxiv.org/abs/2012.14740)
8
+ 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 ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "coordinate_size": 171,
4
+ "fast_qkv": false,
5
+ "gradient_checkpointing": false,
6
+ "has_relative_attention_bias": true,
7
+ "has_spatial_attention_bias": true,
8
+ "has_visual_segment_embedding": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "image_feature_pool_shape": [
13
+ 7,
14
+ 7,
15
+ 256
16
+ ],
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "layer_norm_eps": 1e-12,
20
+ "max_2d_position_embeddings": 1024,
21
+ "max_position_embeddings": 512,
22
+ "max_rel_2d_pos": 256,
23
+ "max_rel_pos": 128,
24
+ "model_type": "layoutlmv2",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "output_past": true,
28
+ "pad_token_id": 0,
29
+ "shape_size": 170,
30
+ "rel_2d_pos_bins": 64,
31
+ "rel_pos_bins": 32,
32
+ "transformers_version": "4.5.1",
33
+ "type_vocab_size": 2,
34
+ "vocab_size": 30522
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94fa102e8f8b6ad05e2c3ec95ed995ff2418df7d43aa462197665b6751cefc02
3
+ size 1705962979
vocab.txt ADDED
The diff for this file is too large to render. See raw diff