Upload 2 files
Browse files- t3_cfg.safetensors +3 -0
- tokenizer_jp.json +418 -0
t3_cfg.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fe5fe2a96e64dfb5ce54e2e31d371f8bb41ae4e1382b80b3c1836c3df7dcab8
|
3 |
+
size 2129654648
|
tokenizer_jp.json
ADDED
@@ -0,0 +1,418 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "[STOP]",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "[UNK]",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "[SPACE]",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 256,
|
35 |
+
"content": "[START]",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
}
|
42 |
+
],
|
43 |
+
"normalizer": null,
|
44 |
+
"pre_tokenizer": {
|
45 |
+
"type": "Whitespace"
|
46 |
+
},
|
47 |
+
"post_processor": null,
|
48 |
+
"decoder": null,
|
49 |
+
"model": {
|
50 |
+
"type": "BPE",
|
51 |
+
"dropout": null,
|
52 |
+
"unk_token": "[UNK]",
|
53 |
+
"continuing_subword_prefix": null,
|
54 |
+
"end_of_word_suffix": null,
|
55 |
+
"fuse_unk": false,
|
56 |
+
"byte_fallback": false,
|
57 |
+
"vocab": {
|
58 |
+
"[STOP]": 0,
|
59 |
+
"[UNK]": 1,
|
60 |
+
"[SPACE]": 2,
|
61 |
+
"!": 3,
|
62 |
+
"%": 4,
|
63 |
+
"&": 5,
|
64 |
+
"'": 6,
|
65 |
+
",": 7,
|
66 |
+
"-": 8,
|
67 |
+
".": 9,
|
68 |
+
"0": 10,
|
69 |
+
"1": 11,
|
70 |
+
"2": 12,
|
71 |
+
"3": 13,
|
72 |
+
"4": 14,
|
73 |
+
"5": 15,
|
74 |
+
"6": 16,
|
75 |
+
"7": 17,
|
76 |
+
"8": 18,
|
77 |
+
"9": 19,
|
78 |
+
"?": 20,
|
79 |
+
"a": 21,
|
80 |
+
"b": 22,
|
81 |
+
"c": 23,
|
82 |
+
"d": 24,
|
83 |
+
"e": 25,
|
84 |
+
"f": 26,
|
85 |
+
"g": 27,
|
86 |
+
"h": 28,
|
87 |
+
"i": 29,
|
88 |
+
"j": 30,
|
89 |
+
"k": 31,
|
90 |
+
"l": 32,
|
91 |
+
"m": 33,
|
92 |
+
"n": 34,
|
93 |
+
"o": 35,
|
94 |
+
"p": 36,
|
95 |
+
"q": 37,
|
96 |
+
"r": 38,
|
97 |
+
"s": 39,
|
98 |
+
"t": 40,
|
99 |
+
"u": 41,
|
100 |
+
"v": 42,
|
101 |
+
"w": 43,
|
102 |
+
"x": 44,
|
103 |
+
"y": 45,
|
104 |
+
"z": 46,
|
105 |
+
"ร": 47,
|
106 |
+
"ฮฒ": 48,
|
107 |
+
"ะฐ": 49,
|
108 |
+
"ะฑ": 50,
|
109 |
+
"ะธ": 51,
|
110 |
+
"ะบ": 52,
|
111 |
+
"ะป": 53,
|
112 |
+
"ะพ": 54,
|
113 |
+
"ะฟ": 55,
|
114 |
+
"ั": 56,
|
115 |
+
"ั": 57,
|
116 |
+
"ุ": 58,
|
117 |
+
"โฆ": 59,
|
118 |
+
"โ": 60,
|
119 |
+
"โ
ฑ": 61,
|
120 |
+
"โ ": 62,
|
121 |
+
"โก": 63,
|
122 |
+
"โฃ": 64,
|
123 |
+
"โค": 65,
|
124 |
+
"โ": 66,
|
125 |
+
"ใ": 67,
|
126 |
+
"ใ": 68,
|
127 |
+
"ใ
": 69,
|
128 |
+
"ใ": 70,
|
129 |
+
"ใ": 71,
|
130 |
+
"ใ": 72,
|
131 |
+
"ใ": 73,
|
132 |
+
"ใ": 74,
|
133 |
+
"ใ": 75,
|
134 |
+
"ใ": 76,
|
135 |
+
"ใ": 77,
|
136 |
+
"ใ
": 78,
|
137 |
+
"ใ": 79,
|
138 |
+
"ใ": 80,
|
139 |
+
"ใ": 81,
|
140 |
+
"ใ": 82,
|
141 |
+
"ใ": 83,
|
142 |
+
"ใ": 84,
|
143 |
+
"ใ": 85,
|
144 |
+
"ใ": 86,
|
145 |
+
"ใ": 87,
|
146 |
+
"ใ": 88,
|
147 |
+
"ใ": 89,
|
148 |
+
"ใ": 90,
|
149 |
+
"ใ": 91,
|
150 |
+
"ใ": 92,
|
151 |
+
"ใ": 93,
|
152 |
+
"ใ": 94,
|
153 |
+
"ใ": 95,
|
154 |
+
"ใ": 96,
|
155 |
+
"ใ": 97,
|
156 |
+
"ใ": 98,
|
157 |
+
"ใ": 99,
|
158 |
+
"ใ": 100,
|
159 |
+
"ใ": 101,
|
160 |
+
"ใ": 102,
|
161 |
+
"ใ": 103,
|
162 |
+
"ใ": 104,
|
163 |
+
"ใ ": 105,
|
164 |
+
"ใก": 106,
|
165 |
+
"ใข": 107,
|
166 |
+
"ใฃ": 108,
|
167 |
+
"ใค": 109,
|
168 |
+
"ใฅ": 110,
|
169 |
+
"ใฆ": 111,
|
170 |
+
"ใง": 112,
|
171 |
+
"ใจ": 113,
|
172 |
+
"ใฉ": 114,
|
173 |
+
"ใช": 115,
|
174 |
+
"ใซ": 116,
|
175 |
+
"ใฌ": 117,
|
176 |
+
"ใญ": 118,
|
177 |
+
"ใฎ": 119,
|
178 |
+
"ใฏ": 120,
|
179 |
+
"ใฐ": 121,
|
180 |
+
"ใฑ": 122,
|
181 |
+
"ใฒ": 123,
|
182 |
+
"ใณ": 124,
|
183 |
+
"ใด": 125,
|
184 |
+
"ใต": 126,
|
185 |
+
"ใถ": 127,
|
186 |
+
"ใท": 128,
|
187 |
+
"ใธ": 129,
|
188 |
+
"ใน": 130,
|
189 |
+
"ใบ": 131,
|
190 |
+
"ใป": 132,
|
191 |
+
"ใผ": 133,
|
192 |
+
"ใฝ": 134,
|
193 |
+
"ใพ": 135,
|
194 |
+
"ใฟ": 136,
|
195 |
+
"ใ": 137,
|
196 |
+
"ใ": 138,
|
197 |
+
"ใ": 139,
|
198 |
+
"ใ": 140,
|
199 |
+
"ใ": 141,
|
200 |
+
"ใ
": 142,
|
201 |
+
"ใ": 143,
|
202 |
+
"ใ": 144,
|
203 |
+
"ใ": 145,
|
204 |
+
"ใ": 146,
|
205 |
+
"ใ": 147,
|
206 |
+
"ใ": 148,
|
207 |
+
"ใ": 149,
|
208 |
+
"ใ": 150,
|
209 |
+
"ใ": 151,
|
210 |
+
"ใ": 152,
|
211 |
+
"ใ": 153,
|
212 |
+
"ใ": 154,
|
213 |
+
"ใ": 155,
|
214 |
+
"ใป": 156,
|
215 |
+
"ใผ": 157,
|
216 |
+
"ใฃใฆ": 158,
|
217 |
+
"ใฃใ": 159,
|
218 |
+
"ใใ": 160,
|
219 |
+
"ใใ": 161,
|
220 |
+
"ใใ": 162,
|
221 |
+
"ใใ": 163,
|
222 |
+
"ใใฆ": 164,
|
223 |
+
"ใชใ": 165,
|
224 |
+
"ใงใ": 166,
|
225 |
+
"ใชใ": 167,
|
226 |
+
"ใใ": 168,
|
227 |
+
"ใพใ": 169,
|
228 |
+
"ใจใ": 170,
|
229 |
+
"ใใ": 171,
|
230 |
+
"ใใ": 172,
|
231 |
+
"ใใ": 173,
|
232 |
+
"ใฃใจ": 174,
|
233 |
+
"ใใจ": 175,
|
234 |
+
"ใใ": 176,
|
235 |
+
"ใใ": 177,
|
236 |
+
"ใใ": 178,
|
237 |
+
"ใใ": 179,
|
238 |
+
"ใใ": 180,
|
239 |
+
"ใใใ": 181,
|
240 |
+
"ใกใ": 182,
|
241 |
+
"ใใ ": 183,
|
242 |
+
"ใใ": 184,
|
243 |
+
"ใใ": 185,
|
244 |
+
"ใใช": 186,
|
245 |
+
"ใพใใ": 187,
|
246 |
+
"ใใฎ": 188,
|
247 |
+
"ใ
ใ": 189,
|
248 |
+
"ใกใ": 190,
|
249 |
+
"ใใฉ": 191,
|
250 |
+
"ใใ": 192,
|
251 |
+
"ใใ": 193,
|
252 |
+
"ใใ": 194,
|
253 |
+
"ใใ": 195,
|
254 |
+
"ใใฎ": 196,
|
255 |
+
"ใกใใฃใจ": 197,
|
256 |
+
"ใใ": 198,
|
257 |
+
"ใใง": 199,
|
258 |
+
"ใจใ": 200,
|
259 |
+
"ใใฎ": 201,
|
260 |
+
"ใซใช": 202,
|
261 |
+
"ใใฎ": 203,
|
262 |
+
"ใใฆ": 204,
|
263 |
+
"ใชใ": 205,
|
264 |
+
"ใใใ": 206,
|
265 |
+
"ใใ": 207,
|
266 |
+
"ใจใใ": 208,
|
267 |
+
"ใใใ": 209,
|
268 |
+
"ใใ": 210,
|
269 |
+
"ใจใใ": 211,
|
270 |
+
"ใชใใ": 212,
|
271 |
+
"ใฟใช": 213,
|
272 |
+
"ใฏใ": 214,
|
273 |
+
"ใใ": 215,
|
274 |
+
"ใใ": 216,
|
275 |
+
"ใฎใง": 217,
|
276 |
+
"ใใใใจใ": 218,
|
277 |
+
"ใปใ": 219,
|
278 |
+
"ใใช": 220,
|
279 |
+
"ใใพใ": 221,
|
280 |
+
"ใใ": 222,
|
281 |
+
"ใใ": 223,
|
282 |
+
"ใใใ": 224,
|
283 |
+
"ใใ": 225,
|
284 |
+
"ใใ": 226,
|
285 |
+
"ใฉใ": 227,
|
286 |
+
"ใงใ": 228,
|
287 |
+
"ใฟใใ": 229,
|
288 |
+
"ใใ": 230,
|
289 |
+
"ใฏใช": 231,
|
290 |
+
"ใใ": 232,
|
291 |
+
"ใใฆ": 233,
|
292 |
+
"ใใ": 234,
|
293 |
+
"ใจใ": 235,
|
294 |
+
"ใใฎ": 236,
|
295 |
+
"ใใ": 237,
|
296 |
+
"ใใฎ": 238,
|
297 |
+
"ใ ใ": 239,
|
298 |
+
"ใใงใ": 240,
|
299 |
+
"ใใฏ": 241,
|
300 |
+
"ใใ": 242,
|
301 |
+
"ใปใ": 243,
|
302 |
+
"ใใฎ": 244,
|
303 |
+
"ใใ": 245,
|
304 |
+
"ใฟใใใช": 246,
|
305 |
+
"ใ ใฃใ": 247,
|
306 |
+
"ใซใ": 248,
|
307 |
+
"ใฃใฆใใ": 249,
|
308 |
+
"ใใฎใ": 250,
|
309 |
+
"ใใ": 251,
|
310 |
+
"ใใใ ": 252,
|
311 |
+
"ใซใก": 253,
|
312 |
+
"ใงใ": 254,
|
313 |
+
"ใงใฏ": 255,
|
314 |
+
"[START]": 256
|
315 |
+
},
|
316 |
+
"merges": [
|
317 |
+
"ใฃ ใฆ",
|
318 |
+
"ใฃ ใ",
|
319 |
+
"ใ ใ",
|
320 |
+
"ใ ใ",
|
321 |
+
"ใ ใ",
|
322 |
+
"ใ ใ",
|
323 |
+
"ใ ใฆ",
|
324 |
+
"ใช ใ",
|
325 |
+
"ใง ใ",
|
326 |
+
"ใช ใ",
|
327 |
+
"ใ ใ",
|
328 |
+
"ใพ ใ",
|
329 |
+
"ใจ ใ",
|
330 |
+
"ใ ใ",
|
331 |
+
"ใ ใ",
|
332 |
+
"ใ ใ",
|
333 |
+
"ใฃ ใจ",
|
334 |
+
"ใ ใจ",
|
335 |
+
"ใ ใ",
|
336 |
+
"ใ ใ",
|
337 |
+
"ใ ใ",
|
338 |
+
"ใ ใ",
|
339 |
+
"ใ ใ",
|
340 |
+
"ใ ใใ",
|
341 |
+
"ใก ใ",
|
342 |
+
"ใ ใ ",
|
343 |
+
"ใ ใ",
|
344 |
+
"ใ ใ",
|
345 |
+
"ใ ใช",
|
346 |
+
"ใพ ใใ",
|
347 |
+
"ใ ใฎ",
|
348 |
+
"ใ
ใ",
|
349 |
+
"ใก ใ",
|
350 |
+
"ใ ใฉ",
|
351 |
+
"ใ ใ",
|
352 |
+
"ใ ใ",
|
353 |
+
"ใ ใ",
|
354 |
+
"ใ ใ",
|
355 |
+
"ใ ใฎ",
|
356 |
+
"ใกใ ใฃใจ",
|
357 |
+
"ใ ใ",
|
358 |
+
"ใ ใง",
|
359 |
+
"ใจ ใ",
|
360 |
+
"ใ ใฎ",
|
361 |
+
"ใซ ใช",
|
362 |
+
"ใ ใฎ",
|
363 |
+
"ใ ใฆ",
|
364 |
+
"ใช ใ",
|
365 |
+
"ใ ใใ",
|
366 |
+
"ใ ใ",
|
367 |
+
"ใจ ใใ",
|
368 |
+
"ใใ ใ",
|
369 |
+
"ใ ใ",
|
370 |
+
"ใจ ใใ",
|
371 |
+
"ใชใ ใ",
|
372 |
+
"ใฟ ใช",
|
373 |
+
"ใฏ ใ",
|
374 |
+
"ใ ใ",
|
375 |
+
"ใ ใ",
|
376 |
+
"ใฎ ใง",
|
377 |
+
"ใใใ ใจใ",
|
378 |
+
"ใป ใ",
|
379 |
+
"ใ ใช",
|
380 |
+
"ใ ใพใ",
|
381 |
+
"ใ ใ",
|
382 |
+
"ใ ใ",
|
383 |
+
"ใ ใใ",
|
384 |
+
"ใ ใ",
|
385 |
+
"ใ ใ",
|
386 |
+
"ใฉ ใ",
|
387 |
+
"ใง ใ",
|
388 |
+
"๏ฟฝ๏ฟฝ๏ฟฝ ใใ",
|
389 |
+
"ใ ใ",
|
390 |
+
"ใฏ ใช",
|
391 |
+
"ใ ใ",
|
392 |
+
"ใ ใฆ",
|
393 |
+
"ใ ใ",
|
394 |
+
"ใจ ใ",
|
395 |
+
"ใ ใฎ",
|
396 |
+
"ใ ใ",
|
397 |
+
"ใ ใฎ",
|
398 |
+
"ใ ใ",
|
399 |
+
"ใ ใงใ",
|
400 |
+
"ใ ใฏ",
|
401 |
+
"ใ ใ",
|
402 |
+
"ใป ใ",
|
403 |
+
"ใ ใฎ",
|
404 |
+
"ใ ใ",
|
405 |
+
"ใฟใใ ใช",
|
406 |
+
"ใ ใฃใ",
|
407 |
+
"ใซ ใ",
|
408 |
+
"ใฃใฆ ใใ",
|
409 |
+
"ใใฎ ใ",
|
410 |
+
"ใ ใ",
|
411 |
+
"ใใ ใ ",
|
412 |
+
"ใซ ใก",
|
413 |
+
"ใง ใ",
|
414 |
+
"ใง ใฏ"
|
415 |
+
],
|
416 |
+
"language": "multi"
|
417 |
+
}
|
418 |
+
}
|