Delete converted_tokenizer
Browse files- converted_tokenizer/added_tokens.json +0 -98
- converted_tokenizer/merges.txt +0 -0
- converted_tokenizer/special_tokens_map.json +0 -30
- converted_tokenizer/tokenizer.json +0 -0
- converted_tokenizer/tokenizer.model +0 -3
- converted_tokenizer/tokenizer.vocab +0 -0
- converted_tokenizer/tokenizer_config.json +0 -782
- converted_tokenizer/vocab.json +0 -0
converted_tokenizer/added_tokens.json
DELETED
@@ -1,98 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"<|dummy_0|>": 100256,
|
3 |
-
"<|endoftext|>": 100257,
|
4 |
-
"<|fim_prefix|>": 100258,
|
5 |
-
"<|fim_middle|>": 100259,
|
6 |
-
"<|fim_suffix|>": 100260,
|
7 |
-
"<|dummy_1|>": 100261,
|
8 |
-
"<|dummy_2|>": 100262,
|
9 |
-
"<|dummy_3|>": 100263,
|
10 |
-
"<|im_start|>": 100264,
|
11 |
-
"<|im_end|>": 100265,
|
12 |
-
"<|im_sep|>": 100266,
|
13 |
-
"<|dummy_4|>": 100267,
|
14 |
-
"<|dummy_5|>": 100268,
|
15 |
-
"<|dummy_6|>": 100269,
|
16 |
-
"<|dummy_7|>": 100270,
|
17 |
-
"<|dummy_8|>": 100271,
|
18 |
-
"<|dummy_9|>": 100272,
|
19 |
-
"<|dummy_10|>": 100273,
|
20 |
-
"<|dummy_11|>": 100274,
|
21 |
-
"<|dummy_12|>": 100275,
|
22 |
-
"<|endofprompt|>": 100276,
|
23 |
-
"<|dummy_13|>": 100277,
|
24 |
-
"<|dummy_14|>": 100278,
|
25 |
-
"<|dummy_15|>": 100279,
|
26 |
-
"<|dummy_16|>": 100280,
|
27 |
-
"<|dummy_17|>": 100281,
|
28 |
-
"<|dummy_18|>": 100282,
|
29 |
-
"<|dummy_19|>": 100283,
|
30 |
-
"<|dummy_20|>": 100284,
|
31 |
-
"<|dummy_21|>": 100285,
|
32 |
-
"<|dummy_22|>": 100286,
|
33 |
-
"<|dummy_23|>": 100287,
|
34 |
-
"<|dummy_24|>": 100288,
|
35 |
-
"<|dummy_25|>": 100289,
|
36 |
-
"<|dummy_26|>": 100290,
|
37 |
-
"<|dummy_27|>": 100291,
|
38 |
-
"<|dummy_28|>": 100292,
|
39 |
-
"<|dummy_29|>": 100293,
|
40 |
-
"<|dummy_30|>": 100294,
|
41 |
-
"<|dummy_31|>": 100295,
|
42 |
-
"<|dummy_32|>": 100296,
|
43 |
-
"<|dummy_33|>": 100297,
|
44 |
-
"<|dummy_34|>": 100298,
|
45 |
-
"<|dummy_35|>": 100299,
|
46 |
-
"<|dummy_36|>": 100300,
|
47 |
-
"<|dummy_37|>": 100301,
|
48 |
-
"<|dummy_38|>": 100302,
|
49 |
-
"<|dummy_39|>": 100303,
|
50 |
-
"<|dummy_40|>": 100304,
|
51 |
-
"<|dummy_41|>": 100305,
|
52 |
-
"<|dummy_42|>": 100306,
|
53 |
-
"<|dummy_43|>": 100307,
|
54 |
-
"<|dummy_44|>": 100308,
|
55 |
-
"<|dummy_45|>": 100309,
|
56 |
-
"<|dummy_46|>": 100310,
|
57 |
-
"<|dummy_47|>": 100311,
|
58 |
-
"<|dummy_48|>": 100312,
|
59 |
-
"<|dummy_49|>": 100313,
|
60 |
-
"<|dummy_50|>": 100314,
|
61 |
-
"<|dummy_51|>": 100315,
|
62 |
-
"<|dummy_52|>": 100316,
|
63 |
-
"<|dummy_53|>": 100317,
|
64 |
-
"<|dummy_54|>": 100318,
|
65 |
-
"<|dummy_55|>": 100319,
|
66 |
-
"<|dummy_56|>": 100320,
|
67 |
-
"<|dummy_57|>": 100321,
|
68 |
-
"<|dummy_58|>": 100322,
|
69 |
-
"<|dummy_59|>": 100323,
|
70 |
-
"<|dummy_60|>": 100324,
|
71 |
-
"<|dummy_61|>": 100325,
|
72 |
-
"<|dummy_62|>": 100326,
|
73 |
-
"<|dummy_63|>": 100327,
|
74 |
-
"<|dummy_64|>": 100328,
|
75 |
-
"<|dummy_65|>": 100329,
|
76 |
-
"<|dummy_66|>": 100330,
|
77 |
-
"<|dummy_67|>": 100331,
|
78 |
-
"<|dummy_68|>": 100332,
|
79 |
-
"<|dummy_69|>": 100333,
|
80 |
-
"<|dummy_70|>": 100334,
|
81 |
-
"<|dummy_71|>": 100335,
|
82 |
-
"<|dummy_72|>": 100336,
|
83 |
-
"<|dummy_73|>": 100337,
|
84 |
-
"<|dummy_74|>": 100338,
|
85 |
-
"<|dummy_75|>": 100339,
|
86 |
-
"<|dummy_76|>": 100340,
|
87 |
-
"<|dummy_77|>": 100341,
|
88 |
-
"<|dummy_78|>": 100342,
|
89 |
-
"<|dummy_79|>": 100343,
|
90 |
-
"<|dummy_80|>": 100344,
|
91 |
-
"<|dummy_81|>": 100345,
|
92 |
-
"<|dummy_82|>": 100346,
|
93 |
-
"<|dummy_83|>": 100347,
|
94 |
-
"<|dummy_84|>": 100348,
|
95 |
-
"<|dummy_85|>": 100349,
|
96 |
-
"<|dummy_86|>": 100350,
|
97 |
-
"<|dummy_87|>": 100351
|
98 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
converted_tokenizer/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
converted_tokenizer/special_tokens_map.json
DELETED
@@ -1,30 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<|endoftext|>",
|
4 |
-
"lstrip": true,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": true,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": true,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": true,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": true,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": true,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<|endoftext|>",
|
25 |
-
"lstrip": true,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": true,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
converted_tokenizer/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
converted_tokenizer/tokenizer.model
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:475f185a58f385f91e8343803a71cde136c5f3b47026b0c8583953c287104cff
|
3 |
-
size 2038397
|
|
|
|
|
|
|
|
converted_tokenizer/tokenizer.vocab
DELETED
The diff for this file is too large to render.
See raw diff
|
|
converted_tokenizer/tokenizer_config.json
DELETED
@@ -1,782 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"100256": {
|
5 |
-
"content": "<|dummy_0|>",
|
6 |
-
"lstrip": true,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": true,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"100257": {
|
13 |
-
"content": "<|endoftext|>",
|
14 |
-
"lstrip": true,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": true,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"100258": {
|
21 |
-
"content": "<|fim_prefix|>",
|
22 |
-
"lstrip": true,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": true,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
-
},
|
28 |
-
"100259": {
|
29 |
-
"content": "<|fim_middle|>",
|
30 |
-
"lstrip": true,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": true,
|
33 |
-
"single_word": false,
|
34 |
-
"special": true
|
35 |
-
},
|
36 |
-
"100260": {
|
37 |
-
"content": "<|fim_suffix|>",
|
38 |
-
"lstrip": true,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": true,
|
41 |
-
"single_word": false,
|
42 |
-
"special": true
|
43 |
-
},
|
44 |
-
"100261": {
|
45 |
-
"content": "<|dummy_1|>",
|
46 |
-
"lstrip": true,
|
47 |
-
"normalized": false,
|
48 |
-
"rstrip": true,
|
49 |
-
"single_word": false,
|
50 |
-
"special": true
|
51 |
-
},
|
52 |
-
"100262": {
|
53 |
-
"content": "<|dummy_2|>",
|
54 |
-
"lstrip": true,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": true,
|
57 |
-
"single_word": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
"100263": {
|
61 |
-
"content": "<|dummy_3|>",
|
62 |
-
"lstrip": true,
|
63 |
-
"normalized": false,
|
64 |
-
"rstrip": true,
|
65 |
-
"single_word": false,
|
66 |
-
"special": true
|
67 |
-
},
|
68 |
-
"100264": {
|
69 |
-
"content": "<|im_start|>",
|
70 |
-
"lstrip": true,
|
71 |
-
"normalized": false,
|
72 |
-
"rstrip": true,
|
73 |
-
"single_word": false,
|
74 |
-
"special": true
|
75 |
-
},
|
76 |
-
"100265": {
|
77 |
-
"content": "<|im_end|>",
|
78 |
-
"lstrip": true,
|
79 |
-
"normalized": false,
|
80 |
-
"rstrip": true,
|
81 |
-
"single_word": false,
|
82 |
-
"special": true
|
83 |
-
},
|
84 |
-
"100266": {
|
85 |
-
"content": "<|im_sep|>",
|
86 |
-
"lstrip": true,
|
87 |
-
"normalized": false,
|
88 |
-
"rstrip": true,
|
89 |
-
"single_word": false,
|
90 |
-
"special": true
|
91 |
-
},
|
92 |
-
"100267": {
|
93 |
-
"content": "<|dummy_4|>",
|
94 |
-
"lstrip": true,
|
95 |
-
"normalized": false,
|
96 |
-
"rstrip": true,
|
97 |
-
"single_word": false,
|
98 |
-
"special": true
|
99 |
-
},
|
100 |
-
"100268": {
|
101 |
-
"content": "<|dummy_5|>",
|
102 |
-
"lstrip": true,
|
103 |
-
"normalized": false,
|
104 |
-
"rstrip": true,
|
105 |
-
"single_word": false,
|
106 |
-
"special": true
|
107 |
-
},
|
108 |
-
"100269": {
|
109 |
-
"content": "<|dummy_6|>",
|
110 |
-
"lstrip": true,
|
111 |
-
"normalized": false,
|
112 |
-
"rstrip": true,
|
113 |
-
"single_word": false,
|
114 |
-
"special": true
|
115 |
-
},
|
116 |
-
"100270": {
|
117 |
-
"content": "<|dummy_7|>",
|
118 |
-
"lstrip": true,
|
119 |
-
"normalized": false,
|
120 |
-
"rstrip": true,
|
121 |
-
"single_word": false,
|
122 |
-
"special": true
|
123 |
-
},
|
124 |
-
"100271": {
|
125 |
-
"content": "<|dummy_8|>",
|
126 |
-
"lstrip": true,
|
127 |
-
"normalized": false,
|
128 |
-
"rstrip": true,
|
129 |
-
"single_word": false,
|
130 |
-
"special": true
|
131 |
-
},
|
132 |
-
"100272": {
|
133 |
-
"content": "<|dummy_9|>",
|
134 |
-
"lstrip": true,
|
135 |
-
"normalized": false,
|
136 |
-
"rstrip": true,
|
137 |
-
"single_word": false,
|
138 |
-
"special": true
|
139 |
-
},
|
140 |
-
"100273": {
|
141 |
-
"content": "<|dummy_10|>",
|
142 |
-
"lstrip": true,
|
143 |
-
"normalized": false,
|
144 |
-
"rstrip": true,
|
145 |
-
"single_word": false,
|
146 |
-
"special": true
|
147 |
-
},
|
148 |
-
"100274": {
|
149 |
-
"content": "<|dummy_11|>",
|
150 |
-
"lstrip": true,
|
151 |
-
"normalized": false,
|
152 |
-
"rstrip": true,
|
153 |
-
"single_word": false,
|
154 |
-
"special": true
|
155 |
-
},
|
156 |
-
"100275": {
|
157 |
-
"content": "<|dummy_12|>",
|
158 |
-
"lstrip": true,
|
159 |
-
"normalized": false,
|
160 |
-
"rstrip": true,
|
161 |
-
"single_word": false,
|
162 |
-
"special": true
|
163 |
-
},
|
164 |
-
"100276": {
|
165 |
-
"content": "<|endofprompt|>",
|
166 |
-
"lstrip": true,
|
167 |
-
"normalized": false,
|
168 |
-
"rstrip": true,
|
169 |
-
"single_word": false,
|
170 |
-
"special": true
|
171 |
-
},
|
172 |
-
"100277": {
|
173 |
-
"content": "<|dummy_13|>",
|
174 |
-
"lstrip": true,
|
175 |
-
"normalized": false,
|
176 |
-
"rstrip": true,
|
177 |
-
"single_word": false,
|
178 |
-
"special": true
|
179 |
-
},
|
180 |
-
"100278": {
|
181 |
-
"content": "<|dummy_14|>",
|
182 |
-
"lstrip": true,
|
183 |
-
"normalized": false,
|
184 |
-
"rstrip": true,
|
185 |
-
"single_word": false,
|
186 |
-
"special": true
|
187 |
-
},
|
188 |
-
"100279": {
|
189 |
-
"content": "<|dummy_15|>",
|
190 |
-
"lstrip": true,
|
191 |
-
"normalized": false,
|
192 |
-
"rstrip": true,
|
193 |
-
"single_word": false,
|
194 |
-
"special": true
|
195 |
-
},
|
196 |
-
"100280": {
|
197 |
-
"content": "<|dummy_16|>",
|
198 |
-
"lstrip": true,
|
199 |
-
"normalized": false,
|
200 |
-
"rstrip": true,
|
201 |
-
"single_word": false,
|
202 |
-
"special": true
|
203 |
-
},
|
204 |
-
"100281": {
|
205 |
-
"content": "<|dummy_17|>",
|
206 |
-
"lstrip": true,
|
207 |
-
"normalized": false,
|
208 |
-
"rstrip": true,
|
209 |
-
"single_word": false,
|
210 |
-
"special": true
|
211 |
-
},
|
212 |
-
"100282": {
|
213 |
-
"content": "<|dummy_18|>",
|
214 |
-
"lstrip": true,
|
215 |
-
"normalized": false,
|
216 |
-
"rstrip": true,
|
217 |
-
"single_word": false,
|
218 |
-
"special": true
|
219 |
-
},
|
220 |
-
"100283": {
|
221 |
-
"content": "<|dummy_19|>",
|
222 |
-
"lstrip": true,
|
223 |
-
"normalized": false,
|
224 |
-
"rstrip": true,
|
225 |
-
"single_word": false,
|
226 |
-
"special": true
|
227 |
-
},
|
228 |
-
"100284": {
|
229 |
-
"content": "<|dummy_20|>",
|
230 |
-
"lstrip": true,
|
231 |
-
"normalized": false,
|
232 |
-
"rstrip": true,
|
233 |
-
"single_word": false,
|
234 |
-
"special": true
|
235 |
-
},
|
236 |
-
"100285": {
|
237 |
-
"content": "<|dummy_21|>",
|
238 |
-
"lstrip": true,
|
239 |
-
"normalized": false,
|
240 |
-
"rstrip": true,
|
241 |
-
"single_word": false,
|
242 |
-
"special": true
|
243 |
-
},
|
244 |
-
"100286": {
|
245 |
-
"content": "<|dummy_22|>",
|
246 |
-
"lstrip": true,
|
247 |
-
"normalized": false,
|
248 |
-
"rstrip": true,
|
249 |
-
"single_word": false,
|
250 |
-
"special": true
|
251 |
-
},
|
252 |
-
"100287": {
|
253 |
-
"content": "<|dummy_23|>",
|
254 |
-
"lstrip": true,
|
255 |
-
"normalized": false,
|
256 |
-
"rstrip": true,
|
257 |
-
"single_word": false,
|
258 |
-
"special": true
|
259 |
-
},
|
260 |
-
"100288": {
|
261 |
-
"content": "<|dummy_24|>",
|
262 |
-
"lstrip": true,
|
263 |
-
"normalized": false,
|
264 |
-
"rstrip": true,
|
265 |
-
"single_word": false,
|
266 |
-
"special": true
|
267 |
-
},
|
268 |
-
"100289": {
|
269 |
-
"content": "<|dummy_25|>",
|
270 |
-
"lstrip": true,
|
271 |
-
"normalized": false,
|
272 |
-
"rstrip": true,
|
273 |
-
"single_word": false,
|
274 |
-
"special": true
|
275 |
-
},
|
276 |
-
"100290": {
|
277 |
-
"content": "<|dummy_26|>",
|
278 |
-
"lstrip": true,
|
279 |
-
"normalized": false,
|
280 |
-
"rstrip": true,
|
281 |
-
"single_word": false,
|
282 |
-
"special": true
|
283 |
-
},
|
284 |
-
"100291": {
|
285 |
-
"content": "<|dummy_27|>",
|
286 |
-
"lstrip": true,
|
287 |
-
"normalized": false,
|
288 |
-
"rstrip": true,
|
289 |
-
"single_word": false,
|
290 |
-
"special": true
|
291 |
-
},
|
292 |
-
"100292": {
|
293 |
-
"content": "<|dummy_28|>",
|
294 |
-
"lstrip": true,
|
295 |
-
"normalized": false,
|
296 |
-
"rstrip": true,
|
297 |
-
"single_word": false,
|
298 |
-
"special": true
|
299 |
-
},
|
300 |
-
"100293": {
|
301 |
-
"content": "<|dummy_29|>",
|
302 |
-
"lstrip": true,
|
303 |
-
"normalized": false,
|
304 |
-
"rstrip": true,
|
305 |
-
"single_word": false,
|
306 |
-
"special": true
|
307 |
-
},
|
308 |
-
"100294": {
|
309 |
-
"content": "<|dummy_30|>",
|
310 |
-
"lstrip": true,
|
311 |
-
"normalized": false,
|
312 |
-
"rstrip": true,
|
313 |
-
"single_word": false,
|
314 |
-
"special": true
|
315 |
-
},
|
316 |
-
"100295": {
|
317 |
-
"content": "<|dummy_31|>",
|
318 |
-
"lstrip": true,
|
319 |
-
"normalized": false,
|
320 |
-
"rstrip": true,
|
321 |
-
"single_word": false,
|
322 |
-
"special": true
|
323 |
-
},
|
324 |
-
"100296": {
|
325 |
-
"content": "<|dummy_32|>",
|
326 |
-
"lstrip": true,
|
327 |
-
"normalized": false,
|
328 |
-
"rstrip": true,
|
329 |
-
"single_word": false,
|
330 |
-
"special": true
|
331 |
-
},
|
332 |
-
"100297": {
|
333 |
-
"content": "<|dummy_33|>",
|
334 |
-
"lstrip": true,
|
335 |
-
"normalized": false,
|
336 |
-
"rstrip": true,
|
337 |
-
"single_word": false,
|
338 |
-
"special": true
|
339 |
-
},
|
340 |
-
"100298": {
|
341 |
-
"content": "<|dummy_34|>",
|
342 |
-
"lstrip": true,
|
343 |
-
"normalized": false,
|
344 |
-
"rstrip": true,
|
345 |
-
"single_word": false,
|
346 |
-
"special": true
|
347 |
-
},
|
348 |
-
"100299": {
|
349 |
-
"content": "<|dummy_35|>",
|
350 |
-
"lstrip": true,
|
351 |
-
"normalized": false,
|
352 |
-
"rstrip": true,
|
353 |
-
"single_word": false,
|
354 |
-
"special": true
|
355 |
-
},
|
356 |
-
"100300": {
|
357 |
-
"content": "<|dummy_36|>",
|
358 |
-
"lstrip": true,
|
359 |
-
"normalized": false,
|
360 |
-
"rstrip": true,
|
361 |
-
"single_word": false,
|
362 |
-
"special": true
|
363 |
-
},
|
364 |
-
"100301": {
|
365 |
-
"content": "<|dummy_37|>",
|
366 |
-
"lstrip": true,
|
367 |
-
"normalized": false,
|
368 |
-
"rstrip": true,
|
369 |
-
"single_word": false,
|
370 |
-
"special": true
|
371 |
-
},
|
372 |
-
"100302": {
|
373 |
-
"content": "<|dummy_38|>",
|
374 |
-
"lstrip": true,
|
375 |
-
"normalized": false,
|
376 |
-
"rstrip": true,
|
377 |
-
"single_word": false,
|
378 |
-
"special": true
|
379 |
-
},
|
380 |
-
"100303": {
|
381 |
-
"content": "<|dummy_39|>",
|
382 |
-
"lstrip": true,
|
383 |
-
"normalized": false,
|
384 |
-
"rstrip": true,
|
385 |
-
"single_word": false,
|
386 |
-
"special": true
|
387 |
-
},
|
388 |
-
"100304": {
|
389 |
-
"content": "<|dummy_40|>",
|
390 |
-
"lstrip": true,
|
391 |
-
"normalized": false,
|
392 |
-
"rstrip": true,
|
393 |
-
"single_word": false,
|
394 |
-
"special": true
|
395 |
-
},
|
396 |
-
"100305": {
|
397 |
-
"content": "<|dummy_41|>",
|
398 |
-
"lstrip": true,
|
399 |
-
"normalized": false,
|
400 |
-
"rstrip": true,
|
401 |
-
"single_word": false,
|
402 |
-
"special": true
|
403 |
-
},
|
404 |
-
"100306": {
|
405 |
-
"content": "<|dummy_42|>",
|
406 |
-
"lstrip": true,
|
407 |
-
"normalized": false,
|
408 |
-
"rstrip": true,
|
409 |
-
"single_word": false,
|
410 |
-
"special": true
|
411 |
-
},
|
412 |
-
"100307": {
|
413 |
-
"content": "<|dummy_43|>",
|
414 |
-
"lstrip": true,
|
415 |
-
"normalized": false,
|
416 |
-
"rstrip": true,
|
417 |
-
"single_word": false,
|
418 |
-
"special": true
|
419 |
-
},
|
420 |
-
"100308": {
|
421 |
-
"content": "<|dummy_44|>",
|
422 |
-
"lstrip": true,
|
423 |
-
"normalized": false,
|
424 |
-
"rstrip": true,
|
425 |
-
"single_word": false,
|
426 |
-
"special": true
|
427 |
-
},
|
428 |
-
"100309": {
|
429 |
-
"content": "<|dummy_45|>",
|
430 |
-
"lstrip": true,
|
431 |
-
"normalized": false,
|
432 |
-
"rstrip": true,
|
433 |
-
"single_word": false,
|
434 |
-
"special": true
|
435 |
-
},
|
436 |
-
"100310": {
|
437 |
-
"content": "<|dummy_46|>",
|
438 |
-
"lstrip": true,
|
439 |
-
"normalized": false,
|
440 |
-
"rstrip": true,
|
441 |
-
"single_word": false,
|
442 |
-
"special": true
|
443 |
-
},
|
444 |
-
"100311": {
|
445 |
-
"content": "<|dummy_47|>",
|
446 |
-
"lstrip": true,
|
447 |
-
"normalized": false,
|
448 |
-
"rstrip": true,
|
449 |
-
"single_word": false,
|
450 |
-
"special": true
|
451 |
-
},
|
452 |
-
"100312": {
|
453 |
-
"content": "<|dummy_48|>",
|
454 |
-
"lstrip": true,
|
455 |
-
"normalized": false,
|
456 |
-
"rstrip": true,
|
457 |
-
"single_word": false,
|
458 |
-
"special": true
|
459 |
-
},
|
460 |
-
"100313": {
|
461 |
-
"content": "<|dummy_49|>",
|
462 |
-
"lstrip": true,
|
463 |
-
"normalized": false,
|
464 |
-
"rstrip": true,
|
465 |
-
"single_word": false,
|
466 |
-
"special": true
|
467 |
-
},
|
468 |
-
"100314": {
|
469 |
-
"content": "<|dummy_50|>",
|
470 |
-
"lstrip": true,
|
471 |
-
"normalized": false,
|
472 |
-
"rstrip": true,
|
473 |
-
"single_word": false,
|
474 |
-
"special": true
|
475 |
-
},
|
476 |
-
"100315": {
|
477 |
-
"content": "<|dummy_51|>",
|
478 |
-
"lstrip": true,
|
479 |
-
"normalized": false,
|
480 |
-
"rstrip": true,
|
481 |
-
"single_word": false,
|
482 |
-
"special": true
|
483 |
-
},
|
484 |
-
"100316": {
|
485 |
-
"content": "<|dummy_52|>",
|
486 |
-
"lstrip": true,
|
487 |
-
"normalized": false,
|
488 |
-
"rstrip": true,
|
489 |
-
"single_word": false,
|
490 |
-
"special": true
|
491 |
-
},
|
492 |
-
"100317": {
|
493 |
-
"content": "<|dummy_53|>",
|
494 |
-
"lstrip": true,
|
495 |
-
"normalized": false,
|
496 |
-
"rstrip": true,
|
497 |
-
"single_word": false,
|
498 |
-
"special": true
|
499 |
-
},
|
500 |
-
"100318": {
|
501 |
-
"content": "<|dummy_54|>",
|
502 |
-
"lstrip": true,
|
503 |
-
"normalized": false,
|
504 |
-
"rstrip": true,
|
505 |
-
"single_word": false,
|
506 |
-
"special": true
|
507 |
-
},
|
508 |
-
"100319": {
|
509 |
-
"content": "<|dummy_55|>",
|
510 |
-
"lstrip": true,
|
511 |
-
"normalized": false,
|
512 |
-
"rstrip": true,
|
513 |
-
"single_word": false,
|
514 |
-
"special": true
|
515 |
-
},
|
516 |
-
"100320": {
|
517 |
-
"content": "<|dummy_56|>",
|
518 |
-
"lstrip": true,
|
519 |
-
"normalized": false,
|
520 |
-
"rstrip": true,
|
521 |
-
"single_word": false,
|
522 |
-
"special": true
|
523 |
-
},
|
524 |
-
"100321": {
|
525 |
-
"content": "<|dummy_57|>",
|
526 |
-
"lstrip": true,
|
527 |
-
"normalized": false,
|
528 |
-
"rstrip": true,
|
529 |
-
"single_word": false,
|
530 |
-
"special": true
|
531 |
-
},
|
532 |
-
"100322": {
|
533 |
-
"content": "<|dummy_58|>",
|
534 |
-
"lstrip": true,
|
535 |
-
"normalized": false,
|
536 |
-
"rstrip": true,
|
537 |
-
"single_word": false,
|
538 |
-
"special": true
|
539 |
-
},
|
540 |
-
"100323": {
|
541 |
-
"content": "<|dummy_59|>",
|
542 |
-
"lstrip": true,
|
543 |
-
"normalized": false,
|
544 |
-
"rstrip": true,
|
545 |
-
"single_word": false,
|
546 |
-
"special": true
|
547 |
-
},
|
548 |
-
"100324": {
|
549 |
-
"content": "<|dummy_60|>",
|
550 |
-
"lstrip": true,
|
551 |
-
"normalized": false,
|
552 |
-
"rstrip": true,
|
553 |
-
"single_word": false,
|
554 |
-
"special": true
|
555 |
-
},
|
556 |
-
"100325": {
|
557 |
-
"content": "<|dummy_61|>",
|
558 |
-
"lstrip": true,
|
559 |
-
"normalized": false,
|
560 |
-
"rstrip": true,
|
561 |
-
"single_word": false,
|
562 |
-
"special": true
|
563 |
-
},
|
564 |
-
"100326": {
|
565 |
-
"content": "<|dummy_62|>",
|
566 |
-
"lstrip": true,
|
567 |
-
"normalized": false,
|
568 |
-
"rstrip": true,
|
569 |
-
"single_word": false,
|
570 |
-
"special": true
|
571 |
-
},
|
572 |
-
"100327": {
|
573 |
-
"content": "<|dummy_63|>",
|
574 |
-
"lstrip": true,
|
575 |
-
"normalized": false,
|
576 |
-
"rstrip": true,
|
577 |
-
"single_word": false,
|
578 |
-
"special": true
|
579 |
-
},
|
580 |
-
"100328": {
|
581 |
-
"content": "<|dummy_64|>",
|
582 |
-
"lstrip": true,
|
583 |
-
"normalized": false,
|
584 |
-
"rstrip": true,
|
585 |
-
"single_word": false,
|
586 |
-
"special": true
|
587 |
-
},
|
588 |
-
"100329": {
|
589 |
-
"content": "<|dummy_65|>",
|
590 |
-
"lstrip": true,
|
591 |
-
"normalized": false,
|
592 |
-
"rstrip": true,
|
593 |
-
"single_word": false,
|
594 |
-
"special": true
|
595 |
-
},
|
596 |
-
"100330": {
|
597 |
-
"content": "<|dummy_66|>",
|
598 |
-
"lstrip": true,
|
599 |
-
"normalized": false,
|
600 |
-
"rstrip": true,
|
601 |
-
"single_word": false,
|
602 |
-
"special": true
|
603 |
-
},
|
604 |
-
"100331": {
|
605 |
-
"content": "<|dummy_67|>",
|
606 |
-
"lstrip": true,
|
607 |
-
"normalized": false,
|
608 |
-
"rstrip": true,
|
609 |
-
"single_word": false,
|
610 |
-
"special": true
|
611 |
-
},
|
612 |
-
"100332": {
|
613 |
-
"content": "<|dummy_68|>",
|
614 |
-
"lstrip": true,
|
615 |
-
"normalized": false,
|
616 |
-
"rstrip": true,
|
617 |
-
"single_word": false,
|
618 |
-
"special": true
|
619 |
-
},
|
620 |
-
"100333": {
|
621 |
-
"content": "<|dummy_69|>",
|
622 |
-
"lstrip": true,
|
623 |
-
"normalized": false,
|
624 |
-
"rstrip": true,
|
625 |
-
"single_word": false,
|
626 |
-
"special": true
|
627 |
-
},
|
628 |
-
"100334": {
|
629 |
-
"content": "<|dummy_70|>",
|
630 |
-
"lstrip": true,
|
631 |
-
"normalized": false,
|
632 |
-
"rstrip": true,
|
633 |
-
"single_word": false,
|
634 |
-
"special": true
|
635 |
-
},
|
636 |
-
"100335": {
|
637 |
-
"content": "<|dummy_71|>",
|
638 |
-
"lstrip": true,
|
639 |
-
"normalized": false,
|
640 |
-
"rstrip": true,
|
641 |
-
"single_word": false,
|
642 |
-
"special": true
|
643 |
-
},
|
644 |
-
"100336": {
|
645 |
-
"content": "<|dummy_72|>",
|
646 |
-
"lstrip": true,
|
647 |
-
"normalized": false,
|
648 |
-
"rstrip": true,
|
649 |
-
"single_word": false,
|
650 |
-
"special": true
|
651 |
-
},
|
652 |
-
"100337": {
|
653 |
-
"content": "<|dummy_73|>",
|
654 |
-
"lstrip": true,
|
655 |
-
"normalized": false,
|
656 |
-
"rstrip": true,
|
657 |
-
"single_word": false,
|
658 |
-
"special": true
|
659 |
-
},
|
660 |
-
"100338": {
|
661 |
-
"content": "<|dummy_74|>",
|
662 |
-
"lstrip": true,
|
663 |
-
"normalized": false,
|
664 |
-
"rstrip": true,
|
665 |
-
"single_word": false,
|
666 |
-
"special": true
|
667 |
-
},
|
668 |
-
"100339": {
|
669 |
-
"content": "<|dummy_75|>",
|
670 |
-
"lstrip": true,
|
671 |
-
"normalized": false,
|
672 |
-
"rstrip": true,
|
673 |
-
"single_word": false,
|
674 |
-
"special": true
|
675 |
-
},
|
676 |
-
"100340": {
|
677 |
-
"content": "<|dummy_76|>",
|
678 |
-
"lstrip": true,
|
679 |
-
"normalized": false,
|
680 |
-
"rstrip": true,
|
681 |
-
"single_word": false,
|
682 |
-
"special": true
|
683 |
-
},
|
684 |
-
"100341": {
|
685 |
-
"content": "<|dummy_77|>",
|
686 |
-
"lstrip": true,
|
687 |
-
"normalized": false,
|
688 |
-
"rstrip": true,
|
689 |
-
"single_word": false,
|
690 |
-
"special": true
|
691 |
-
},
|
692 |
-
"100342": {
|
693 |
-
"content": "<|dummy_78|>",
|
694 |
-
"lstrip": true,
|
695 |
-
"normalized": false,
|
696 |
-
"rstrip": true,
|
697 |
-
"single_word": false,
|
698 |
-
"special": true
|
699 |
-
},
|
700 |
-
"100343": {
|
701 |
-
"content": "<|dummy_79|>",
|
702 |
-
"lstrip": true,
|
703 |
-
"normalized": false,
|
704 |
-
"rstrip": true,
|
705 |
-
"single_word": false,
|
706 |
-
"special": true
|
707 |
-
},
|
708 |
-
"100344": {
|
709 |
-
"content": "<|dummy_80|>",
|
710 |
-
"lstrip": true,
|
711 |
-
"normalized": false,
|
712 |
-
"rstrip": true,
|
713 |
-
"single_word": false,
|
714 |
-
"special": true
|
715 |
-
},
|
716 |
-
"100345": {
|
717 |
-
"content": "<|dummy_81|>",
|
718 |
-
"lstrip": true,
|
719 |
-
"normalized": false,
|
720 |
-
"rstrip": true,
|
721 |
-
"single_word": false,
|
722 |
-
"special": true
|
723 |
-
},
|
724 |
-
"100346": {
|
725 |
-
"content": "<|dummy_82|>",
|
726 |
-
"lstrip": true,
|
727 |
-
"normalized": false,
|
728 |
-
"rstrip": true,
|
729 |
-
"single_word": false,
|
730 |
-
"special": true
|
731 |
-
},
|
732 |
-
"100347": {
|
733 |
-
"content": "<|dummy_83|>",
|
734 |
-
"lstrip": true,
|
735 |
-
"normalized": false,
|
736 |
-
"rstrip": true,
|
737 |
-
"single_word": false,
|
738 |
-
"special": true
|
739 |
-
},
|
740 |
-
"100348": {
|
741 |
-
"content": "<|dummy_84|>",
|
742 |
-
"lstrip": true,
|
743 |
-
"normalized": false,
|
744 |
-
"rstrip": true,
|
745 |
-
"single_word": false,
|
746 |
-
"special": true
|
747 |
-
},
|
748 |
-
"100349": {
|
749 |
-
"content": "<|dummy_85|>",
|
750 |
-
"lstrip": true,
|
751 |
-
"normalized": false,
|
752 |
-
"rstrip": true,
|
753 |
-
"single_word": false,
|
754 |
-
"special": true
|
755 |
-
},
|
756 |
-
"100350": {
|
757 |
-
"content": "<|dummy_86|>",
|
758 |
-
"lstrip": true,
|
759 |
-
"normalized": false,
|
760 |
-
"rstrip": true,
|
761 |
-
"single_word": false,
|
762 |
-
"special": true
|
763 |
-
},
|
764 |
-
"100351": {
|
765 |
-
"content": "<|dummy_87|>",
|
766 |
-
"lstrip": true,
|
767 |
-
"normalized": false,
|
768 |
-
"rstrip": true,
|
769 |
-
"single_word": false,
|
770 |
-
"special": true
|
771 |
-
}
|
772 |
-
},
|
773 |
-
"bos_token": "<|endoftext|>",
|
774 |
-
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}",
|
775 |
-
"clean_up_tokenization_spaces": false,
|
776 |
-
"eos_token": "<|endoftext|>",
|
777 |
-
"extra_special_tokens": {},
|
778 |
-
"model_max_length": 16384,
|
779 |
-
"pad_token": "<|endoftext|>",
|
780 |
-
"tokenizer_class": "GPT2Tokenizer",
|
781 |
-
"unk_token": "<|endoftext|>"
|
782 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
converted_tokenizer/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|