Upload tokenizer
Browse files- added_tokens.json +40 -0
- special_tokens_map.json +70 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +383 -0
added_tokens.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|action|>": 32018,
|
3 |
+
"<|belief|>": 32005,
|
4 |
+
"<|context|>": 32029,
|
5 |
+
"<|endofaction|>": 32020,
|
6 |
+
"<|endofbelief|>": 32035,
|
7 |
+
"<|endofcontext|>": 32002,
|
8 |
+
"<|endofresponse|>": 32028,
|
9 |
+
"<|endofuseremotion|>": 32032,
|
10 |
+
"<|response|>": 32024,
|
11 |
+
"<|system|>": 32023,
|
12 |
+
"<|useremotion|>": 32013,
|
13 |
+
"<|user|>": 32014,
|
14 |
+
"[address]": 32000,
|
15 |
+
"[area]": 32015,
|
16 |
+
"[arriveby]": 32037,
|
17 |
+
"[bookday]": 32010,
|
18 |
+
"[bookpeople]": 32034,
|
19 |
+
"[bookstay]": 32016,
|
20 |
+
"[booktime]": 32027,
|
21 |
+
"[choice]": 32033,
|
22 |
+
"[day]": 32009,
|
23 |
+
"[department]": 32001,
|
24 |
+
"[departure]": 32004,
|
25 |
+
"[destination]": 32006,
|
26 |
+
"[duration]": 32030,
|
27 |
+
"[entrancefee]": 32008,
|
28 |
+
"[food]": 32017,
|
29 |
+
"[leaveat]": 32007,
|
30 |
+
"[name]": 32012,
|
31 |
+
"[openhours]": 32011,
|
32 |
+
"[phone]": 32025,
|
33 |
+
"[postcode]": 32026,
|
34 |
+
"[price]": 32021,
|
35 |
+
"[pricerange]": 32022,
|
36 |
+
"[ref]": 32036,
|
37 |
+
"[stars]": 32003,
|
38 |
+
"[trainid]": 32019,
|
39 |
+
"[type]": 32031
|
40 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[address]",
|
4 |
+
"[department]",
|
5 |
+
"<|endofcontext|>",
|
6 |
+
"[stars]",
|
7 |
+
"[departure]",
|
8 |
+
"<|belief|>",
|
9 |
+
"[destination]",
|
10 |
+
"[leaveat]",
|
11 |
+
"[entrancefee]",
|
12 |
+
"[day]",
|
13 |
+
"[bookday]",
|
14 |
+
"[openhours]",
|
15 |
+
"[name]",
|
16 |
+
"<|useremotion|>",
|
17 |
+
"<|user|>",
|
18 |
+
"[area]",
|
19 |
+
"[bookstay]",
|
20 |
+
"[food]",
|
21 |
+
"<|action|>",
|
22 |
+
"[trainid]",
|
23 |
+
"<|endofaction|>",
|
24 |
+
"[price]",
|
25 |
+
"[pricerange]",
|
26 |
+
"<|system|>",
|
27 |
+
"<|response|>",
|
28 |
+
"[phone]",
|
29 |
+
"[postcode]",
|
30 |
+
"[booktime]",
|
31 |
+
"<|endofresponse|>",
|
32 |
+
"<|context|>",
|
33 |
+
"[duration]",
|
34 |
+
"[type]",
|
35 |
+
"<|endofuseremotion|>",
|
36 |
+
"[choice]",
|
37 |
+
"[bookpeople]",
|
38 |
+
"<|endofbelief|>",
|
39 |
+
"[ref]",
|
40 |
+
"[arriveby]"
|
41 |
+
],
|
42 |
+
"bos_token": {
|
43 |
+
"content": "<s>",
|
44 |
+
"lstrip": false,
|
45 |
+
"normalized": false,
|
46 |
+
"rstrip": false,
|
47 |
+
"single_word": false
|
48 |
+
},
|
49 |
+
"eos_token": {
|
50 |
+
"content": "</s>",
|
51 |
+
"lstrip": false,
|
52 |
+
"normalized": false,
|
53 |
+
"rstrip": false,
|
54 |
+
"single_word": false
|
55 |
+
},
|
56 |
+
"pad_token": {
|
57 |
+
"content": "</s>",
|
58 |
+
"lstrip": false,
|
59 |
+
"normalized": false,
|
60 |
+
"rstrip": false,
|
61 |
+
"single_word": false
|
62 |
+
},
|
63 |
+
"unk_token": {
|
64 |
+
"content": "<unk>",
|
65 |
+
"lstrip": false,
|
66 |
+
"normalized": false,
|
67 |
+
"rstrip": false,
|
68 |
+
"single_word": false
|
69 |
+
}
|
70 |
+
}
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "[address]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32001": {
|
36 |
+
"content": "[department]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"32002": {
|
44 |
+
"content": "<|endofcontext|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"32003": {
|
52 |
+
"content": "[stars]",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"32004": {
|
60 |
+
"content": "[departure]",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"32005": {
|
68 |
+
"content": "<|belief|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"32006": {
|
76 |
+
"content": "[destination]",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"32007": {
|
84 |
+
"content": "[leaveat]",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"32008": {
|
92 |
+
"content": "[entrancefee]",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"32009": {
|
100 |
+
"content": "[day]",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"32010": {
|
108 |
+
"content": "[bookday]",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"32011": {
|
116 |
+
"content": "[openhours]",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"32012": {
|
124 |
+
"content": "[name]",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"32013": {
|
132 |
+
"content": "<|useremotion|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"32014": {
|
140 |
+
"content": "<|user|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"32015": {
|
148 |
+
"content": "[area]",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"32016": {
|
156 |
+
"content": "[bookstay]",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"32017": {
|
164 |
+
"content": "[food]",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"32018": {
|
172 |
+
"content": "<|action|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"32019": {
|
180 |
+
"content": "[trainid]",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"32020": {
|
188 |
+
"content": "<|endofaction|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"32021": {
|
196 |
+
"content": "[price]",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"32022": {
|
204 |
+
"content": "[pricerange]",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"32023": {
|
212 |
+
"content": "<|system|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"32024": {
|
220 |
+
"content": "<|response|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"32025": {
|
228 |
+
"content": "[phone]",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"32026": {
|
236 |
+
"content": "[postcode]",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"32027": {
|
244 |
+
"content": "[booktime]",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"32028": {
|
252 |
+
"content": "<|endofresponse|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"32029": {
|
260 |
+
"content": "<|context|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"32030": {
|
268 |
+
"content": "[duration]",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"32031": {
|
276 |
+
"content": "[type]",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"32032": {
|
284 |
+
"content": "<|endofuseremotion|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"32033": {
|
292 |
+
"content": "[choice]",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"32034": {
|
300 |
+
"content": "[bookpeople]",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"32035": {
|
308 |
+
"content": "<|endofbelief|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"32036": {
|
316 |
+
"content": "[ref]",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"32037": {
|
324 |
+
"content": "[arriveby]",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
}
|
331 |
+
},
|
332 |
+
"additional_special_tokens": [
|
333 |
+
"[address]",
|
334 |
+
"[department]",
|
335 |
+
"<|endofcontext|>",
|
336 |
+
"[stars]",
|
337 |
+
"[departure]",
|
338 |
+
"<|belief|>",
|
339 |
+
"[destination]",
|
340 |
+
"[leaveat]",
|
341 |
+
"[entrancefee]",
|
342 |
+
"[day]",
|
343 |
+
"[bookday]",
|
344 |
+
"[openhours]",
|
345 |
+
"[name]",
|
346 |
+
"<|useremotion|>",
|
347 |
+
"<|user|>",
|
348 |
+
"[area]",
|
349 |
+
"[bookstay]",
|
350 |
+
"[food]",
|
351 |
+
"<|action|>",
|
352 |
+
"[trainid]",
|
353 |
+
"<|endofaction|>",
|
354 |
+
"[price]",
|
355 |
+
"[pricerange]",
|
356 |
+
"<|system|>",
|
357 |
+
"<|response|>",
|
358 |
+
"[phone]",
|
359 |
+
"[postcode]",
|
360 |
+
"[booktime]",
|
361 |
+
"<|endofresponse|>",
|
362 |
+
"<|context|>",
|
363 |
+
"[duration]",
|
364 |
+
"[type]",
|
365 |
+
"<|endofuseremotion|>",
|
366 |
+
"[choice]",
|
367 |
+
"[bookpeople]",
|
368 |
+
"<|endofbelief|>",
|
369 |
+
"[ref]",
|
370 |
+
"[arriveby]"
|
371 |
+
],
|
372 |
+
"bos_token": "<s>",
|
373 |
+
"clean_up_tokenization_spaces": false,
|
374 |
+
"eos_token": "</s>",
|
375 |
+
"legacy": false,
|
376 |
+
"model_max_length": 1000000000000000019884624838656,
|
377 |
+
"pad_token": "</s>",
|
378 |
+
"padding_side": "right",
|
379 |
+
"sp_model_kwargs": {},
|
380 |
+
"tokenizer_class": "LlamaTokenizer",
|
381 |
+
"unk_token": "<unk>",
|
382 |
+
"use_default_system_prompt": false
|
383 |
+
}
|