thaind commited on
Commit
fa3d139
1 Parent(s): 85da22c

First version of model finetune layoutlmv2 for japan_eng.

Browse files
config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv2-base-uncased",
3
+ "architectures": [
4
+ "LayoutLMv2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "convert_sync_batchnorm": true,
8
+ "coordinate_size": 128,
9
+ "fast_qkv": true,
10
+ "finetuning_task": "ner",
11
+ "gradient_checkpointing": false,
12
+ "has_relative_attention_bias": true,
13
+ "has_spatial_attention_bias": true,
14
+ "has_visual_segment_embedding": false,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "id2label": {
19
+ "0": "LABEL_0",
20
+ "1": "LABEL_1",
21
+ "2": "LABEL_2",
22
+ "3": "LABEL_3",
23
+ "4": "LABEL_4",
24
+ "5": "LABEL_5",
25
+ "6": "LABEL_6",
26
+ "7": "LABEL_7",
27
+ "8": "LABEL_8",
28
+ "9": "LABEL_9",
29
+ "10": "LABEL_10",
30
+ "11": "LABEL_11",
31
+ "12": "LABEL_12",
32
+ "13": "LABEL_13",
33
+ "14": "LABEL_14",
34
+ "15": "LABEL_15",
35
+ "16": "LABEL_16"
36
+ },
37
+ "image_feature_pool_shape": [
38
+ 7,
39
+ 7,
40
+ 256
41
+ ],
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 3072,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1,
47
+ "LABEL_10": 10,
48
+ "LABEL_11": 11,
49
+ "LABEL_12": 12,
50
+ "LABEL_13": 13,
51
+ "LABEL_14": 14,
52
+ "LABEL_15": 15,
53
+ "LABEL_16": 16,
54
+ "LABEL_2": 2,
55
+ "LABEL_3": 3,
56
+ "LABEL_4": 4,
57
+ "LABEL_5": 5,
58
+ "LABEL_6": 6,
59
+ "LABEL_7": 7,
60
+ "LABEL_8": 8,
61
+ "LABEL_9": 9
62
+ },
63
+ "layer_norm_eps": 1e-12,
64
+ "max_2d_position_embeddings": 1024,
65
+ "max_position_embeddings": 512,
66
+ "max_rel_2d_pos": 256,
67
+ "max_rel_pos": 128,
68
+ "model_type": "layoutlmv2",
69
+ "num_attention_heads": 12,
70
+ "num_hidden_layers": 12,
71
+ "output_past": true,
72
+ "pad_token_id": 0,
73
+ "position_embedding_type": "absolute",
74
+ "rel_2d_pos_bins": 64,
75
+ "rel_pos_bins": 32,
76
+ "shape_size": 128,
77
+ "transformers_version": "4.5.1",
78
+ "type_vocab_size": 2,
79
+ "use_cache": true,
80
+ "vocab_size": 30522
81
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b0a6a29a0ec61a1a7b4068e1c4b4340199b7fe072aad69e13d979c81501837
3
+ size 802305938
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/layoutlmv2-base-uncased", "do_basic_tokenize": true, "never_split": null}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00314c15c084414b7d409c42c18a24596eaff5814c716047087f32076756a7b7
3
+ size 2351
vocab.txt ADDED
The diff for this file is too large to render. See raw diff