avemio-digital
commited on
Commit
•
264259e
1
Parent(s):
abf5e9d
Upload tokenizer
Browse files- added_tokens.json +18 -0
- special_tokens_map.json +50 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +190 -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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": true,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": true,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": true,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": true,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "[Partially supported]",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": true,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "[Utility:1]",
|
39 |
+
"lstrip": true,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "[Utility:2]",
|
47 |
+
"lstrip": true,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "[No support / Contradictory]",
|
55 |
+
"lstrip": true,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "[Retrieval]",
|
63 |
+
"lstrip": true,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<paragraph>",
|
71 |
+
"lstrip": true,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "[Continue to Use Evidence]",
|
79 |
+
"lstrip": true,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "[Relevant]",
|
87 |
+
"lstrip": true,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "[Utility:3]",
|
95 |
+
"lstrip": true,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "[Utility:5]",
|
103 |
+
"lstrip": true,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "[No Retrieval]",
|
111 |
+
"lstrip": true,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"32011": {
|
118 |
+
"content": "[Irrelevant]",
|
119 |
+
"lstrip": true,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": true,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"32012": {
|
126 |
+
"content": "[Utility:4]",
|
127 |
+
"lstrip": true,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": true,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"32013": {
|
134 |
+
"content": "</paragraph>",
|
135 |
+
"lstrip": true,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": true,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"32014": {
|
142 |
+
"content": "[Fully supported]",
|
143 |
+
"lstrip": true,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": true,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"32015": {
|
150 |
+
"content": "<pad>",
|
151 |
+
"lstrip": true,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": true,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
}
|
157 |
+
},
|
158 |
+
"additional_special_tokens": [
|
159 |
+
"<unk>",
|
160 |
+
"<s>",
|
161 |
+
"</s>",
|
162 |
+
"[Partially supported]",
|
163 |
+
"[Utility:1]",
|
164 |
+
"[Utility:2]",
|
165 |
+
"[No support / Contradictory]",
|
166 |
+
"[Retrieval]",
|
167 |
+
"<paragraph>",
|
168 |
+
"[Continue to Use Evidence]",
|
169 |
+
"[Relevant]",
|
170 |
+
"[Utility:3]",
|
171 |
+
"[Utility:5]",
|
172 |
+
"[No Retrieval]",
|
173 |
+
"[Irrelevant]",
|
174 |
+
"[Utility:4]",
|
175 |
+
"</paragraph>",
|
176 |
+
"[Fully supported]"
|
177 |
+
],
|
178 |
+
"bos_token": "<s>",
|
179 |
+
"clean_up_tokenization_spaces": false,
|
180 |
+
"eos_token": "</s>",
|
181 |
+
"legacy": true,
|
182 |
+
"model_max_length": 2048,
|
183 |
+
"pad_token": "<pad>",
|
184 |
+
"padding_side": "right",
|
185 |
+
"sp_model_kwargs": {},
|
186 |
+
"spaces_between_special_tokens": false,
|
187 |
+
"tokenizer_class": "LlamaTokenizer",
|
188 |
+
"unk_token": "<unk>",
|
189 |
+
"use_default_system_prompt": true
|
190 |
+
}
|