Hugging Face's logo

docling-project
/
TableFormerV2

Safetensors
TableFormerV2
Model card Files
xet
 Community
1
asnassar commited on
Commit
2aa7366
·
verified ·
1 Parent(s): b94fa99

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +19 -0
  2. generation_config.json +9 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +149 -0
  6. tokenizer_config.json +117 -0
config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "TableFormerV2"
4
+ ],
5
+ "conv_mixer_expansion": 1.0,
6
+ "data_cells": [
7
+ 5,
8
+ 4
9
+ ],
10
+ "dtype": "float32",
11
+ "embed_dim": 512,
12
+ "eos_token_id": 3,
13
+ "ff_dim": 2048,
14
+ "model_type": "TableFormerV2",
15
+ "num_heads": 8,
16
+ "pad_token_id": 0,
17
+ "transformers_version": "4.57.1",
18
+ "vocab_size": 13
19
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": [
5
+ 3
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.57.1"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d376f18421404a991375c82b0b4004b71ba592ff1a74de61c029af715f8b7914
3
+ size 178463068
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<start>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<end>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 512
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "<pad>"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "<pad>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": true,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "[UNK]",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": true,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 2,
40
+ "content": "<start>",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": true,
45
+ "special": true
46
+ },
47
+ {
48
+ "id": 3,
49
+ "content": "<end>",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": true,
54
+ "special": true
55
+ },
56
+ {
57
+ "id": 4,
58
+ "content": "<ecel>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": true,
63
+ "special": false
64
+ },
65
+ {
66
+ "id": 5,
67
+ "content": "<fcel>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": true,
72
+ "special": false
73
+ },
74
+ {
75
+ "id": 6,
76
+ "content": "<lcel>",
77
+ "single_word": false,
78
+ "lstrip": false,
79
+ "rstrip": false,
80
+ "normalized": true,
81
+ "special": false
82
+ },
83
+ {
84
+ "id": 7,
85
+ "content": "<ucel>",
86
+ "single_word": false,
87
+ "lstrip": false,
88
+ "rstrip": false,
89
+ "normalized": true,
90
+ "special": false
91
+ },
92
+ {
93
+ "id": 8,
94
+ "content": "<xcel>",
95
+ "single_word": false,
96
+ "lstrip": false,
97
+ "rstrip": false,
98
+ "normalized": true,
99
+ "special": false
100
+ },
101
+ {
102
+ "id": 9,
103
+ "content": "<nl>",
104
+ "single_word": false,
105
+ "lstrip": false,
106
+ "rstrip": false,
107
+ "normalized": true,
108
+ "special": false
109
+ },
110
+ {
111
+ "id": 10,
112
+ "content": "<ched>",
113
+ "single_word": false,
114
+ "lstrip": false,
115
+ "rstrip": false,
116
+ "normalized": true,
117
+ "special": false
118
+ },
119
+ {
120
+ "id": 11,
121
+ "content": "<rhed>",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": true,
126
+ "special": false
127
+ },
128
+ {
129
+ "id": 12,
130
+ "content": "<srow>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": true,
135
+ "special": false
136
+ }
137
+ ],
138
+ "normalizer": null,
139
+ "pre_tokenizer": null,
140
+ "post_processor": null,
141
+ "decoder": null,
142
+ "model": {
143
+ "type": "WordPiece",
144
+ "unk_token": "[UNK]",
145
+ "continuing_subword_prefix": "##",
146
+ "max_input_chars_per_word": 100,
147
+ "vocab": {}
148
+ }
149
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<start>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<end>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<ecel>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "5": {
44
+ "content": "<fcel>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "6": {
52
+ "content": "<lcel>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "7": {
60
+ "content": "<ucel>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "8": {
68
+ "content": "<xcel>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "9": {
76
+ "content": "<nl>",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "10": {
84
+ "content": "<ched>",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "11": {
92
+ "content": "<rhed>",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "12": {
100
+ "content": "<srow>",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ }
107
+ },
108
+ "bos_token": "<start>",
109
+ "clean_up_tokenization_spaces": false,
110
+ "eos_token": "<end>",
111
+ "extra_special_tokens": {},
112
+ "model_max_length": 512,
113
+ "pad_token": "<pad>",
114
+ "tokenizer_class": "PreTrainedTokenizerFast",
115
+ "unk_token": "[UNK]",
116
+ "vocab_size": 0
117
+ }