Hugging Face's logo

dylan-demand-io
/
merged_model_mistral_tulu_ocr

Text Generation
Transformers
PyTorch
mistral
text-generation-inference
Inference Endpoints
Model card Files Community
dylan-demand-io commited on
Commit
cf48e7e
•
1 Parent(s): f601ca7

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +18 -0
  2. special_tokens_map.json +50 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +187 -0
added_tokens.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</paragraph>": 32013,
3
+ "<pad>": 32015,
4
+ "<paragraph>": 32005,
5
+ "[Continue to Use Evidence]": 32006,
6
+ "[Fully supported]": 32014,
7
+ "[Irrelevant]": 32011,
8
+ "[No Retrieval]": 32010,
9
+ "[No support / Contradictory]": 32003,
10
+ "[Partially supported]": 32000,
11
+ "[Relevant]": 32007,
12
+ "[Retrieval]": 32004,
13
+ "[Utility:1]": 32001,
14
+ "[Utility:2]": 32002,
15
+ "[Utility:3]": 32008,
16
+ "[Utility:4]": 32012,
17
+ "[Utility:5]": 32009
18
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[Partially supported]",
7
+ "[Utility:1]",
8
+ "[Utility:2]",
9
+ "[No support / Contradictory]",
10
+ "[Retrieval]",
11
+ "<paragraph>",
12
+ "[Continue to Use Evidence]",
13
+ "[Relevant]",
14
+ "[Utility:3]",
15
+ "[Utility:5]",
16
+ "[No Retrieval]",
17
+ "[Irrelevant]",
18
+ "[Utility:4]",
19
+ "</paragraph>",
20
+ "[Fully supported]"
21
+ ],
22
+ "bos_token": {
23
+ "content": "<s>",
24
+ "lstrip": true,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false
28
+ },
29
+ "eos_token": {
30
+ "content": "</s>",
31
+ "lstrip": true,
32
+ "normalized": false,
33
+ "rstrip": true,
34
+ "single_word": false
35
+ },
36
+ "pad_token": {
37
+ "content": "<pad>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false
42
+ },
43
+ "unk_token": {
44
+ "content": "<unk>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false
49
+ }
50
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "[Partially supported]",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "[Utility:1]",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "[Utility:2]",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "[No support / Contradictory]",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "[Retrieval]",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<paragraph>",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "[Continue to Use Evidence]",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "[Relevant]",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "[Utility:3]",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "[Utility:5]",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "[No Retrieval]",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "[Irrelevant]",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "[Utility:4]",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "</paragraph>",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "[Fully supported]",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "<pad>",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": true
154
+ }
155
+ },
156
+ "additional_special_tokens": [
157
+ "<unk>",
158
+ "<s>",
159
+ "</s>",
160
+ "[Partially supported]",
161
+ "[Utility:1]",
162
+ "[Utility:2]",
163
+ "[No support / Contradictory]",
164
+ "[Retrieval]",
165
+ "<paragraph>",
166
+ "[Continue to Use Evidence]",
167
+ "[Relevant]",
168
+ "[Utility:3]",
169
+ "[Utility:5]",
170
+ "[No Retrieval]",
171
+ "[Irrelevant]",
172
+ "[Utility:4]",
173
+ "</paragraph>",
174
+ "[Fully supported]"
175
+ ],
176
+ "bos_token": "<s>",
177
+ "clean_up_tokenization_spaces": false,
178
+ "eos_token": "</s>",
179
+ "legacy": true,
180
+ "model_max_length": 1024,
181
+ "pad_token": "<pad>",
182
+ "sp_model_kwargs": {},
183
+ "spaces_between_special_tokens": false,
184
+ "tokenizer_class": "LlamaTokenizer",
185
+ "unk_token": "<unk>",
186
+ "use_default_system_prompt": true
187
+ }