Training done
Browse files- added_tokens.json +86 -0
- preprocessor_config.json +24 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
added_tokens.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_ocr>": 57604,
|
3 |
+
"</s_一般诊疗费>": 57596,
|
4 |
+
"</s_个人现金支付>": 57582,
|
5 |
+
"</s_个人自付>": 57580,
|
6 |
+
"</s_个人账户支付>": 57578,
|
7 |
+
"</s_中成药费>": 57594,
|
8 |
+
"</s_中药饮片>": 57600,
|
9 |
+
"</s_价税合计(大写)>": 57586,
|
10 |
+
"</s_住院天数>": 57534,
|
11 |
+
"</s_入院日期>": 57532,
|
12 |
+
"</s_其他支付>": 57576,
|
13 |
+
"</s_出院日期>": 57530,
|
14 |
+
"</s_化验费>": 57574,
|
15 |
+
"</s_医保类型>": 57572,
|
16 |
+
"</s_医保统筹基金支付>": 57570,
|
17 |
+
"</s_医疗机构类型>": 57568,
|
18 |
+
"</s_医院名称>": 57528,
|
19 |
+
"</s_卫生材料费>": 57566,
|
20 |
+
"</s_合计金额(大写)>": 57564,
|
21 |
+
"</s_复核人>": 57562,
|
22 |
+
"</s_年龄>": 57526,
|
23 |
+
"</s_床位费>": 57560,
|
24 |
+
"</s_开票日期>": 57558,
|
25 |
+
"</s_性别>": 57598,
|
26 |
+
"</s_手术费>": 57556,
|
27 |
+
"</s_护理费>": 57554,
|
28 |
+
"</s_挂号费>": 57592,
|
29 |
+
"</s_收款人>": 57552,
|
30 |
+
"</s_收款单位>": 57550,
|
31 |
+
"</s_校验码>": 57548,
|
32 |
+
"</s_检查费>": 57546,
|
33 |
+
"</s_治疗费>": 57544,
|
34 |
+
"</s_票据代码>": 57542,
|
35 |
+
"</s_票据号码>": 57540,
|
36 |
+
"</s_统筹支付>": 57602,
|
37 |
+
"</s_自付一>": 57590,
|
38 |
+
"</s_自付二>": 57588,
|
39 |
+
"</s_西药费>": 57538,
|
40 |
+
"</s_诊查费>": 57584,
|
41 |
+
"</s_(小写)>": 57536,
|
42 |
+
"<NULL>": 57605,
|
43 |
+
"<s_iitcdip>": 57523,
|
44 |
+
"<s_ocr>": 57603,
|
45 |
+
"<s_synthdog>": 57524,
|
46 |
+
"<s_一般诊疗费>": 57595,
|
47 |
+
"<s_个人现金支付>": 57581,
|
48 |
+
"<s_个人自付>": 57579,
|
49 |
+
"<s_个人账户支付>": 57577,
|
50 |
+
"<s_中成药费>": 57593,
|
51 |
+
"<s_中药饮片>": 57599,
|
52 |
+
"<s_价税合计(大写)>": 57585,
|
53 |
+
"<s_住院天数>": 57533,
|
54 |
+
"<s_入院日期>": 57531,
|
55 |
+
"<s_其他支付>": 57575,
|
56 |
+
"<s_出院日期>": 57529,
|
57 |
+
"<s_化验费>": 57573,
|
58 |
+
"<s_医保类型>": 57571,
|
59 |
+
"<s_医保统筹基金支付>": 57569,
|
60 |
+
"<s_医疗机构类型>": 57567,
|
61 |
+
"<s_医院名称>": 57527,
|
62 |
+
"<s_卫生材料费>": 57565,
|
63 |
+
"<s_合计金额(大写)>": 57563,
|
64 |
+
"<s_复核人>": 57561,
|
65 |
+
"<s_年龄>": 57525,
|
66 |
+
"<s_床位费>": 57559,
|
67 |
+
"<s_开票日期>": 57557,
|
68 |
+
"<s_性别>": 57597,
|
69 |
+
"<s_手术费>": 57555,
|
70 |
+
"<s_护理费>": 57553,
|
71 |
+
"<s_挂号费>": 57591,
|
72 |
+
"<s_收款人>": 57551,
|
73 |
+
"<s_收款单位>": 57549,
|
74 |
+
"<s_校验码>": 57547,
|
75 |
+
"<s_检查费>": 57545,
|
76 |
+
"<s_治疗费>": 57543,
|
77 |
+
"<s_票据代码>": 57541,
|
78 |
+
"<s_票据号码>": 57539,
|
79 |
+
"<s_统筹支付>": 57601,
|
80 |
+
"<s_自付一>": 57589,
|
81 |
+
"<s_自付二>": 57587,
|
82 |
+
"<s_西药费>": 57537,
|
83 |
+
"<s_诊查费>": 57583,
|
84 |
+
"<s_(小写)>": 57535,
|
85 |
+
"<sep/>": 57522
|
86 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_align_long_axis": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"do_thumbnail": true,
|
7 |
+
"feature_extractor_type": "DonutFeatureExtractor",
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_std": [
|
14 |
+
0.5,
|
15 |
+
0.5,
|
16 |
+
0.5
|
17 |
+
],
|
18 |
+
"processor_class": "DonutProcessor",
|
19 |
+
"resample": 2,
|
20 |
+
"size": [
|
21 |
+
960,
|
22 |
+
1280
|
23 |
+
]
|
24 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
3 |
+
size 1296245
|
special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s_iitcdip>",
|
4 |
+
"<s_synthdog>"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"name_or_path": "nielsr/donut-base",
|
14 |
+
"pad_token": "<pad>",
|
15 |
+
"processor_class": "DonutProcessor",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"sp_model_kwargs": {},
|
18 |
+
"special_tokens_map_file": null,
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|