Training in progress, step 1000
Browse files
added_tokens.json
CHANGED
@@ -1,86 +1,86 @@
|
|
1 |
{
|
2 |
-
" ":
|
3 |
-
"%":
|
4 |
-
"0":
|
5 |
-
"1":
|
6 |
-
"2":
|
7 |
-
"3":
|
8 |
-
"4":
|
9 |
-
"5":
|
10 |
-
"8":
|
11 |
-
"9":
|
12 |
"<ctc_blank>": 80,
|
13 |
"<mask>": 79,
|
14 |
-
"À":
|
15 |
-
"Á":
|
16 |
-
"Ê":
|
17 |
-
"Ô":
|
18 |
-
"Ý":
|
19 |
-
"à":
|
20 |
-
"á":
|
21 |
-
"â":
|
22 |
-
"ã":
|
23 |
-
"è":
|
24 |
-
"ì":
|
25 |
-
"í":
|
26 |
-
"ò":
|
27 |
-
"ó":
|
28 |
-
"ô":
|
29 |
-
"õ":
|
30 |
-
"ù":
|
31 |
-
"ú":
|
32 |
-
"ý":
|
33 |
-
"ă":
|
34 |
-
"Đ":
|
35 |
-
"đ":
|
36 |
-
"ĩ":
|
37 |
-
"ũ":
|
38 |
-
"ơ":
|
39 |
-
"ư":
|
40 |
-
"ạ":
|
41 |
-
"ả":
|
42 |
-
"ấ":
|
43 |
-
"ầ":
|
44 |
-
"ẩ":
|
45 |
-
"ẫ":
|
46 |
-
"ậ":
|
47 |
-
"ắ":
|
48 |
-
"ằ":
|
49 |
-
"ẳ":
|
50 |
"ẵ": 117,
|
51 |
-
"ặ":
|
52 |
-
"ẹ":
|
53 |
-
"ẻ":
|
54 |
-
"ẽ":
|
55 |
-
"ế":
|
56 |
-
"ề":
|
57 |
-
"ể":
|
58 |
-
"ễ":
|
59 |
-
"ệ":
|
60 |
-
"ỉ":
|
61 |
-
"ị":
|
62 |
-
"ọ":
|
63 |
-
"ỏ":
|
64 |
-
"ố":
|
65 |
-
"ồ":
|
66 |
-
"ổ":
|
67 |
-
"ỗ":
|
68 |
-
"ộ":
|
69 |
-
"ớ":
|
70 |
-
"ờ":
|
71 |
-
"Ở":
|
72 |
-
"ở":
|
73 |
-
"ỡ":
|
74 |
-
"ợ":
|
75 |
-
"ụ":
|
76 |
-
"ủ":
|
77 |
-
"ứ":
|
78 |
-
"Ừ":
|
79 |
-
"ừ":
|
80 |
-
"ử":
|
81 |
-
"ữ":
|
82 |
-
"ự":
|
83 |
-
"ỳ":
|
84 |
-
"ỷ":
|
85 |
-
"ỹ":
|
86 |
}
|
|
|
1 |
{
|
2 |
+
" ": 100,
|
3 |
+
"%": 107,
|
4 |
+
"0": 132,
|
5 |
+
"1": 90,
|
6 |
+
"2": 94,
|
7 |
+
"3": 131,
|
8 |
+
"4": 119,
|
9 |
+
"5": 92,
|
10 |
+
"8": 95,
|
11 |
+
"9": 151,
|
12 |
"<ctc_blank>": 80,
|
13 |
"<mask>": 79,
|
14 |
+
"À": 134,
|
15 |
+
"Á": 116,
|
16 |
+
"Ê": 125,
|
17 |
+
"Ô": 135,
|
18 |
+
"Ý": 148,
|
19 |
+
"à": 143,
|
20 |
+
"á": 123,
|
21 |
+
"â": 113,
|
22 |
+
"ã": 87,
|
23 |
+
"è": 124,
|
24 |
+
"ì": 126,
|
25 |
+
"í": 154,
|
26 |
+
"ò": 139,
|
27 |
+
"ó": 103,
|
28 |
+
"ô": 153,
|
29 |
+
"õ": 93,
|
30 |
+
"ù": 121,
|
31 |
+
"ú": 122,
|
32 |
+
"ý": 162,
|
33 |
+
"ă": 84,
|
34 |
+
"Đ": 128,
|
35 |
+
"đ": 88,
|
36 |
+
"ĩ": 136,
|
37 |
+
"ũ": 161,
|
38 |
+
"ơ": 138,
|
39 |
+
"ư": 140,
|
40 |
+
"ạ": 108,
|
41 |
+
"ả": 106,
|
42 |
+
"ấ": 149,
|
43 |
+
"ầ": 133,
|
44 |
+
"ẩ": 159,
|
45 |
+
"ẫ": 144,
|
46 |
+
"ậ": 147,
|
47 |
+
"ắ": 102,
|
48 |
+
"ằ": 97,
|
49 |
+
"ẳ": 104,
|
50 |
"ẵ": 117,
|
51 |
+
"ặ": 141,
|
52 |
+
"ẹ": 81,
|
53 |
+
"ẻ": 152,
|
54 |
+
"ẽ": 91,
|
55 |
+
"ế": 137,
|
56 |
+
"ề": 112,
|
57 |
+
"ể": 82,
|
58 |
+
"ễ": 115,
|
59 |
+
"ệ": 83,
|
60 |
+
"ỉ": 99,
|
61 |
+
"ị": 114,
|
62 |
+
"ọ": 129,
|
63 |
+
"ỏ": 89,
|
64 |
+
"ố": 105,
|
65 |
+
"ồ": 101,
|
66 |
+
"ổ": 127,
|
67 |
+
"ỗ": 130,
|
68 |
+
"ộ": 150,
|
69 |
+
"ớ": 160,
|
70 |
+
"ờ": 98,
|
71 |
+
"Ở": 85,
|
72 |
+
"ở": 155,
|
73 |
+
"ỡ": 110,
|
74 |
+
"ợ": 145,
|
75 |
+
"ụ": 96,
|
76 |
+
"ủ": 146,
|
77 |
+
"ứ": 142,
|
78 |
+
"Ừ": 111,
|
79 |
+
"ừ": 157,
|
80 |
+
"ử": 118,
|
81 |
+
"ữ": 156,
|
82 |
+
"ự": 158,
|
83 |
+
"ỳ": 86,
|
84 |
+
"ỷ": 109,
|
85 |
+
"ỹ": 120
|
86 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 578041224
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ceed15499b8876eec5c475909c4b768ba8360faf5332094b71b50bdf653c3e1
|
3 |
size 578041224
|
runs/Sep05_01-39-57_134bc728a688/events.out.tfevents.1725500404.134bc728a688.537.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2674563b75f43751e1c14f48efff63bdd4594f9ad59dd408bf213bb14f114193
|
3 |
+
size 15623
|
tokenizer_config.json
CHANGED
@@ -49,7 +49,7 @@
|
|
49 |
"special": false
|
50 |
},
|
51 |
"81": {
|
52 |
-
"content": "
|
53 |
"lstrip": false,
|
54 |
"normalized": true,
|
55 |
"rstrip": false,
|
@@ -57,7 +57,7 @@
|
|
57 |
"special": false
|
58 |
},
|
59 |
"82": {
|
60 |
-
"content": "
|
61 |
"lstrip": false,
|
62 |
"normalized": true,
|
63 |
"rstrip": false,
|
@@ -65,7 +65,7 @@
|
|
65 |
"special": false
|
66 |
},
|
67 |
"83": {
|
68 |
-
"content": "
|
69 |
"lstrip": false,
|
70 |
"normalized": true,
|
71 |
"rstrip": false,
|
@@ -73,7 +73,7 @@
|
|
73 |
"special": false
|
74 |
},
|
75 |
"84": {
|
76 |
-
"content": "
|
77 |
"lstrip": false,
|
78 |
"normalized": true,
|
79 |
"rstrip": false,
|
@@ -81,7 +81,7 @@
|
|
81 |
"special": false
|
82 |
},
|
83 |
"85": {
|
84 |
-
"content": "
|
85 |
"lstrip": false,
|
86 |
"normalized": true,
|
87 |
"rstrip": false,
|
@@ -89,7 +89,7 @@
|
|
89 |
"special": false
|
90 |
},
|
91 |
"86": {
|
92 |
-
"content": "
|
93 |
"lstrip": false,
|
94 |
"normalized": true,
|
95 |
"rstrip": false,
|
@@ -97,7 +97,7 @@
|
|
97 |
"special": false
|
98 |
},
|
99 |
"87": {
|
100 |
-
"content": "
|
101 |
"lstrip": false,
|
102 |
"normalized": true,
|
103 |
"rstrip": false,
|
@@ -105,7 +105,7 @@
|
|
105 |
"special": false
|
106 |
},
|
107 |
"88": {
|
108 |
-
"content": "
|
109 |
"lstrip": false,
|
110 |
"normalized": true,
|
111 |
"rstrip": false,
|
@@ -113,7 +113,7 @@
|
|
113 |
"special": false
|
114 |
},
|
115 |
"89": {
|
116 |
-
"content": "
|
117 |
"lstrip": false,
|
118 |
"normalized": true,
|
119 |
"rstrip": false,
|
@@ -121,7 +121,7 @@
|
|
121 |
"special": false
|
122 |
},
|
123 |
"90": {
|
124 |
-
"content": "
|
125 |
"lstrip": false,
|
126 |
"normalized": true,
|
127 |
"rstrip": false,
|
@@ -129,7 +129,7 @@
|
|
129 |
"special": false
|
130 |
},
|
131 |
"91": {
|
132 |
-
"content": "
|
133 |
"lstrip": false,
|
134 |
"normalized": true,
|
135 |
"rstrip": false,
|
@@ -137,7 +137,7 @@
|
|
137 |
"special": false
|
138 |
},
|
139 |
"92": {
|
140 |
-
"content": "
|
141 |
"lstrip": false,
|
142 |
"normalized": true,
|
143 |
"rstrip": false,
|
@@ -145,7 +145,7 @@
|
|
145 |
"special": false
|
146 |
},
|
147 |
"93": {
|
148 |
-
"content": "
|
149 |
"lstrip": false,
|
150 |
"normalized": true,
|
151 |
"rstrip": false,
|
@@ -153,7 +153,7 @@
|
|
153 |
"special": false
|
154 |
},
|
155 |
"94": {
|
156 |
-
"content": "
|
157 |
"lstrip": false,
|
158 |
"normalized": true,
|
159 |
"rstrip": false,
|
@@ -161,7 +161,7 @@
|
|
161 |
"special": false
|
162 |
},
|
163 |
"95": {
|
164 |
-
"content": "
|
165 |
"lstrip": false,
|
166 |
"normalized": true,
|
167 |
"rstrip": false,
|
@@ -169,7 +169,7 @@
|
|
169 |
"special": false
|
170 |
},
|
171 |
"96": {
|
172 |
-
"content": "
|
173 |
"lstrip": false,
|
174 |
"normalized": true,
|
175 |
"rstrip": false,
|
@@ -177,7 +177,7 @@
|
|
177 |
"special": false
|
178 |
},
|
179 |
"97": {
|
180 |
-
"content": "
|
181 |
"lstrip": false,
|
182 |
"normalized": true,
|
183 |
"rstrip": false,
|
@@ -185,7 +185,7 @@
|
|
185 |
"special": false
|
186 |
},
|
187 |
"98": {
|
188 |
-
"content": "
|
189 |
"lstrip": false,
|
190 |
"normalized": true,
|
191 |
"rstrip": false,
|
@@ -193,7 +193,7 @@
|
|
193 |
"special": false
|
194 |
},
|
195 |
"99": {
|
196 |
-
"content": "
|
197 |
"lstrip": false,
|
198 |
"normalized": true,
|
199 |
"rstrip": false,
|
@@ -201,7 +201,7 @@
|
|
201 |
"special": false
|
202 |
},
|
203 |
"100": {
|
204 |
-
"content": "
|
205 |
"lstrip": false,
|
206 |
"normalized": true,
|
207 |
"rstrip": false,
|
@@ -209,7 +209,7 @@
|
|
209 |
"special": false
|
210 |
},
|
211 |
"101": {
|
212 |
-
"content": "
|
213 |
"lstrip": false,
|
214 |
"normalized": true,
|
215 |
"rstrip": false,
|
@@ -217,7 +217,7 @@
|
|
217 |
"special": false
|
218 |
},
|
219 |
"102": {
|
220 |
-
"content": "
|
221 |
"lstrip": false,
|
222 |
"normalized": true,
|
223 |
"rstrip": false,
|
@@ -225,7 +225,7 @@
|
|
225 |
"special": false
|
226 |
},
|
227 |
"103": {
|
228 |
-
"content": "
|
229 |
"lstrip": false,
|
230 |
"normalized": true,
|
231 |
"rstrip": false,
|
@@ -233,7 +233,7 @@
|
|
233 |
"special": false
|
234 |
},
|
235 |
"104": {
|
236 |
-
"content": "
|
237 |
"lstrip": false,
|
238 |
"normalized": true,
|
239 |
"rstrip": false,
|
@@ -241,7 +241,7 @@
|
|
241 |
"special": false
|
242 |
},
|
243 |
"105": {
|
244 |
-
"content": "
|
245 |
"lstrip": false,
|
246 |
"normalized": true,
|
247 |
"rstrip": false,
|
@@ -249,7 +249,7 @@
|
|
249 |
"special": false
|
250 |
},
|
251 |
"106": {
|
252 |
-
"content": "
|
253 |
"lstrip": false,
|
254 |
"normalized": true,
|
255 |
"rstrip": false,
|
@@ -257,7 +257,7 @@
|
|
257 |
"special": false
|
258 |
},
|
259 |
"107": {
|
260 |
-
"content": "
|
261 |
"lstrip": false,
|
262 |
"normalized": true,
|
263 |
"rstrip": false,
|
@@ -265,7 +265,7 @@
|
|
265 |
"special": false
|
266 |
},
|
267 |
"108": {
|
268 |
-
"content": "
|
269 |
"lstrip": false,
|
270 |
"normalized": true,
|
271 |
"rstrip": false,
|
@@ -273,7 +273,7 @@
|
|
273 |
"special": false
|
274 |
},
|
275 |
"109": {
|
276 |
-
"content": "
|
277 |
"lstrip": false,
|
278 |
"normalized": true,
|
279 |
"rstrip": false,
|
@@ -281,7 +281,7 @@
|
|
281 |
"special": false
|
282 |
},
|
283 |
"110": {
|
284 |
-
"content": "
|
285 |
"lstrip": false,
|
286 |
"normalized": true,
|
287 |
"rstrip": false,
|
@@ -289,7 +289,7 @@
|
|
289 |
"special": false
|
290 |
},
|
291 |
"111": {
|
292 |
-
"content": "
|
293 |
"lstrip": false,
|
294 |
"normalized": true,
|
295 |
"rstrip": false,
|
@@ -297,7 +297,7 @@
|
|
297 |
"special": false
|
298 |
},
|
299 |
"112": {
|
300 |
-
"content": "
|
301 |
"lstrip": false,
|
302 |
"normalized": true,
|
303 |
"rstrip": false,
|
@@ -305,7 +305,7 @@
|
|
305 |
"special": false
|
306 |
},
|
307 |
"113": {
|
308 |
-
"content": "
|
309 |
"lstrip": false,
|
310 |
"normalized": true,
|
311 |
"rstrip": false,
|
@@ -313,7 +313,7 @@
|
|
313 |
"special": false
|
314 |
},
|
315 |
"114": {
|
316 |
-
"content": "
|
317 |
"lstrip": false,
|
318 |
"normalized": true,
|
319 |
"rstrip": false,
|
@@ -321,7 +321,7 @@
|
|
321 |
"special": false
|
322 |
},
|
323 |
"115": {
|
324 |
-
"content": "
|
325 |
"lstrip": false,
|
326 |
"normalized": true,
|
327 |
"rstrip": false,
|
@@ -329,7 +329,7 @@
|
|
329 |
"special": false
|
330 |
},
|
331 |
"116": {
|
332 |
-
"content": "
|
333 |
"lstrip": false,
|
334 |
"normalized": true,
|
335 |
"rstrip": false,
|
@@ -345,7 +345,7 @@
|
|
345 |
"special": false
|
346 |
},
|
347 |
"118": {
|
348 |
-
"content": "
|
349 |
"lstrip": false,
|
350 |
"normalized": true,
|
351 |
"rstrip": false,
|
@@ -353,7 +353,7 @@
|
|
353 |
"special": false
|
354 |
},
|
355 |
"119": {
|
356 |
-
"content": "
|
357 |
"lstrip": false,
|
358 |
"normalized": true,
|
359 |
"rstrip": false,
|
@@ -361,7 +361,7 @@
|
|
361 |
"special": false
|
362 |
},
|
363 |
"120": {
|
364 |
-
"content": "
|
365 |
"lstrip": false,
|
366 |
"normalized": true,
|
367 |
"rstrip": false,
|
@@ -369,7 +369,7 @@
|
|
369 |
"special": false
|
370 |
},
|
371 |
"121": {
|
372 |
-
"content": "
|
373 |
"lstrip": false,
|
374 |
"normalized": true,
|
375 |
"rstrip": false,
|
@@ -377,7 +377,7 @@
|
|
377 |
"special": false
|
378 |
},
|
379 |
"122": {
|
380 |
-
"content": "
|
381 |
"lstrip": false,
|
382 |
"normalized": true,
|
383 |
"rstrip": false,
|
@@ -385,7 +385,7 @@
|
|
385 |
"special": false
|
386 |
},
|
387 |
"123": {
|
388 |
-
"content": "
|
389 |
"lstrip": false,
|
390 |
"normalized": true,
|
391 |
"rstrip": false,
|
@@ -393,7 +393,7 @@
|
|
393 |
"special": false
|
394 |
},
|
395 |
"124": {
|
396 |
-
"content": "
|
397 |
"lstrip": false,
|
398 |
"normalized": true,
|
399 |
"rstrip": false,
|
@@ -401,7 +401,7 @@
|
|
401 |
"special": false
|
402 |
},
|
403 |
"125": {
|
404 |
-
"content": "
|
405 |
"lstrip": false,
|
406 |
"normalized": true,
|
407 |
"rstrip": false,
|
@@ -409,7 +409,7 @@
|
|
409 |
"special": false
|
410 |
},
|
411 |
"126": {
|
412 |
-
"content": "
|
413 |
"lstrip": false,
|
414 |
"normalized": true,
|
415 |
"rstrip": false,
|
@@ -417,7 +417,7 @@
|
|
417 |
"special": false
|
418 |
},
|
419 |
"127": {
|
420 |
-
"content": "
|
421 |
"lstrip": false,
|
422 |
"normalized": true,
|
423 |
"rstrip": false,
|
@@ -425,7 +425,7 @@
|
|
425 |
"special": false
|
426 |
},
|
427 |
"128": {
|
428 |
-
"content": "
|
429 |
"lstrip": false,
|
430 |
"normalized": true,
|
431 |
"rstrip": false,
|
@@ -433,7 +433,7 @@
|
|
433 |
"special": false
|
434 |
},
|
435 |
"129": {
|
436 |
-
"content": "
|
437 |
"lstrip": false,
|
438 |
"normalized": true,
|
439 |
"rstrip": false,
|
@@ -441,7 +441,7 @@
|
|
441 |
"special": false
|
442 |
},
|
443 |
"130": {
|
444 |
-
"content": "
|
445 |
"lstrip": false,
|
446 |
"normalized": true,
|
447 |
"rstrip": false,
|
@@ -449,7 +449,7 @@
|
|
449 |
"special": false
|
450 |
},
|
451 |
"131": {
|
452 |
-
"content": "
|
453 |
"lstrip": false,
|
454 |
"normalized": true,
|
455 |
"rstrip": false,
|
@@ -457,7 +457,7 @@
|
|
457 |
"special": false
|
458 |
},
|
459 |
"132": {
|
460 |
-
"content": "
|
461 |
"lstrip": false,
|
462 |
"normalized": true,
|
463 |
"rstrip": false,
|
@@ -465,7 +465,7 @@
|
|
465 |
"special": false
|
466 |
},
|
467 |
"133": {
|
468 |
-
"content": "
|
469 |
"lstrip": false,
|
470 |
"normalized": true,
|
471 |
"rstrip": false,
|
@@ -473,7 +473,7 @@
|
|
473 |
"special": false
|
474 |
},
|
475 |
"134": {
|
476 |
-
"content": "
|
477 |
"lstrip": false,
|
478 |
"normalized": true,
|
479 |
"rstrip": false,
|
@@ -481,7 +481,7 @@
|
|
481 |
"special": false
|
482 |
},
|
483 |
"135": {
|
484 |
-
"content": "
|
485 |
"lstrip": false,
|
486 |
"normalized": true,
|
487 |
"rstrip": false,
|
@@ -489,7 +489,7 @@
|
|
489 |
"special": false
|
490 |
},
|
491 |
"136": {
|
492 |
-
"content": "
|
493 |
"lstrip": false,
|
494 |
"normalized": true,
|
495 |
"rstrip": false,
|
@@ -497,7 +497,7 @@
|
|
497 |
"special": false
|
498 |
},
|
499 |
"137": {
|
500 |
-
"content": "
|
501 |
"lstrip": false,
|
502 |
"normalized": true,
|
503 |
"rstrip": false,
|
@@ -505,7 +505,7 @@
|
|
505 |
"special": false
|
506 |
},
|
507 |
"138": {
|
508 |
-
"content": "
|
509 |
"lstrip": false,
|
510 |
"normalized": true,
|
511 |
"rstrip": false,
|
@@ -513,7 +513,7 @@
|
|
513 |
"special": false
|
514 |
},
|
515 |
"139": {
|
516 |
-
"content": "
|
517 |
"lstrip": false,
|
518 |
"normalized": true,
|
519 |
"rstrip": false,
|
@@ -521,7 +521,7 @@
|
|
521 |
"special": false
|
522 |
},
|
523 |
"140": {
|
524 |
-
"content": "
|
525 |
"lstrip": false,
|
526 |
"normalized": true,
|
527 |
"rstrip": false,
|
@@ -529,7 +529,7 @@
|
|
529 |
"special": false
|
530 |
},
|
531 |
"141": {
|
532 |
-
"content": "
|
533 |
"lstrip": false,
|
534 |
"normalized": true,
|
535 |
"rstrip": false,
|
@@ -537,7 +537,7 @@
|
|
537 |
"special": false
|
538 |
},
|
539 |
"142": {
|
540 |
-
"content": "
|
541 |
"lstrip": false,
|
542 |
"normalized": true,
|
543 |
"rstrip": false,
|
@@ -545,7 +545,7 @@
|
|
545 |
"special": false
|
546 |
},
|
547 |
"143": {
|
548 |
-
"content": "
|
549 |
"lstrip": false,
|
550 |
"normalized": true,
|
551 |
"rstrip": false,
|
@@ -553,7 +553,7 @@
|
|
553 |
"special": false
|
554 |
},
|
555 |
"144": {
|
556 |
-
"content": "
|
557 |
"lstrip": false,
|
558 |
"normalized": true,
|
559 |
"rstrip": false,
|
@@ -561,7 +561,7 @@
|
|
561 |
"special": false
|
562 |
},
|
563 |
"145": {
|
564 |
-
"content": "
|
565 |
"lstrip": false,
|
566 |
"normalized": true,
|
567 |
"rstrip": false,
|
@@ -569,7 +569,7 @@
|
|
569 |
"special": false
|
570 |
},
|
571 |
"146": {
|
572 |
-
"content": "
|
573 |
"lstrip": false,
|
574 |
"normalized": true,
|
575 |
"rstrip": false,
|
@@ -577,7 +577,7 @@
|
|
577 |
"special": false
|
578 |
},
|
579 |
"147": {
|
580 |
-
"content": "
|
581 |
"lstrip": false,
|
582 |
"normalized": true,
|
583 |
"rstrip": false,
|
@@ -585,7 +585,7 @@
|
|
585 |
"special": false
|
586 |
},
|
587 |
"148": {
|
588 |
-
"content": "
|
589 |
"lstrip": false,
|
590 |
"normalized": true,
|
591 |
"rstrip": false,
|
@@ -593,7 +593,7 @@
|
|
593 |
"special": false
|
594 |
},
|
595 |
"149": {
|
596 |
-
"content": "
|
597 |
"lstrip": false,
|
598 |
"normalized": true,
|
599 |
"rstrip": false,
|
@@ -601,7 +601,7 @@
|
|
601 |
"special": false
|
602 |
},
|
603 |
"150": {
|
604 |
-
"content": "
|
605 |
"lstrip": false,
|
606 |
"normalized": true,
|
607 |
"rstrip": false,
|
@@ -609,7 +609,7 @@
|
|
609 |
"special": false
|
610 |
},
|
611 |
"151": {
|
612 |
-
"content": "
|
613 |
"lstrip": false,
|
614 |
"normalized": true,
|
615 |
"rstrip": false,
|
@@ -617,7 +617,7 @@
|
|
617 |
"special": false
|
618 |
},
|
619 |
"152": {
|
620 |
-
"content": "
|
621 |
"lstrip": false,
|
622 |
"normalized": true,
|
623 |
"rstrip": false,
|
@@ -625,7 +625,7 @@
|
|
625 |
"special": false
|
626 |
},
|
627 |
"153": {
|
628 |
-
"content": "
|
629 |
"lstrip": false,
|
630 |
"normalized": true,
|
631 |
"rstrip": false,
|
@@ -633,7 +633,7 @@
|
|
633 |
"special": false
|
634 |
},
|
635 |
"154": {
|
636 |
-
"content": "
|
637 |
"lstrip": false,
|
638 |
"normalized": true,
|
639 |
"rstrip": false,
|
@@ -641,7 +641,7 @@
|
|
641 |
"special": false
|
642 |
},
|
643 |
"155": {
|
644 |
-
"content": "
|
645 |
"lstrip": false,
|
646 |
"normalized": true,
|
647 |
"rstrip": false,
|
@@ -649,7 +649,7 @@
|
|
649 |
"special": false
|
650 |
},
|
651 |
"156": {
|
652 |
-
"content": "
|
653 |
"lstrip": false,
|
654 |
"normalized": true,
|
655 |
"rstrip": false,
|
@@ -657,7 +657,7 @@
|
|
657 |
"special": false
|
658 |
},
|
659 |
"157": {
|
660 |
-
"content": "
|
661 |
"lstrip": false,
|
662 |
"normalized": true,
|
663 |
"rstrip": false,
|
@@ -665,7 +665,7 @@
|
|
665 |
"special": false
|
666 |
},
|
667 |
"158": {
|
668 |
-
"content": "
|
669 |
"lstrip": false,
|
670 |
"normalized": true,
|
671 |
"rstrip": false,
|
@@ -673,7 +673,7 @@
|
|
673 |
"special": false
|
674 |
},
|
675 |
"159": {
|
676 |
-
"content": "
|
677 |
"lstrip": false,
|
678 |
"normalized": true,
|
679 |
"rstrip": false,
|
@@ -681,7 +681,7 @@
|
|
681 |
"special": false
|
682 |
},
|
683 |
"160": {
|
684 |
-
"content": "
|
685 |
"lstrip": false,
|
686 |
"normalized": true,
|
687 |
"rstrip": false,
|
@@ -689,7 +689,7 @@
|
|
689 |
"special": false
|
690 |
},
|
691 |
"161": {
|
692 |
-
"content": "
|
693 |
"lstrip": false,
|
694 |
"normalized": true,
|
695 |
"rstrip": false,
|
@@ -697,7 +697,7 @@
|
|
697 |
"special": false
|
698 |
},
|
699 |
"162": {
|
700 |
-
"content": "
|
701 |
"lstrip": false,
|
702 |
"normalized": true,
|
703 |
"rstrip": false,
|
|
|
49 |
"special": false
|
50 |
},
|
51 |
"81": {
|
52 |
+
"content": "ẹ",
|
53 |
"lstrip": false,
|
54 |
"normalized": true,
|
55 |
"rstrip": false,
|
|
|
57 |
"special": false
|
58 |
},
|
59 |
"82": {
|
60 |
+
"content": "ể",
|
61 |
"lstrip": false,
|
62 |
"normalized": true,
|
63 |
"rstrip": false,
|
|
|
65 |
"special": false
|
66 |
},
|
67 |
"83": {
|
68 |
+
"content": "ệ",
|
69 |
"lstrip": false,
|
70 |
"normalized": true,
|
71 |
"rstrip": false,
|
|
|
73 |
"special": false
|
74 |
},
|
75 |
"84": {
|
76 |
+
"content": "ă",
|
77 |
"lstrip": false,
|
78 |
"normalized": true,
|
79 |
"rstrip": false,
|
|
|
81 |
"special": false
|
82 |
},
|
83 |
"85": {
|
84 |
+
"content": "Ở",
|
85 |
"lstrip": false,
|
86 |
"normalized": true,
|
87 |
"rstrip": false,
|
|
|
89 |
"special": false
|
90 |
},
|
91 |
"86": {
|
92 |
+
"content": "ỳ",
|
93 |
"lstrip": false,
|
94 |
"normalized": true,
|
95 |
"rstrip": false,
|
|
|
97 |
"special": false
|
98 |
},
|
99 |
"87": {
|
100 |
+
"content": "ã",
|
101 |
"lstrip": false,
|
102 |
"normalized": true,
|
103 |
"rstrip": false,
|
|
|
105 |
"special": false
|
106 |
},
|
107 |
"88": {
|
108 |
+
"content": "đ",
|
109 |
"lstrip": false,
|
110 |
"normalized": true,
|
111 |
"rstrip": false,
|
|
|
113 |
"special": false
|
114 |
},
|
115 |
"89": {
|
116 |
+
"content": "ỏ",
|
117 |
"lstrip": false,
|
118 |
"normalized": true,
|
119 |
"rstrip": false,
|
|
|
121 |
"special": false
|
122 |
},
|
123 |
"90": {
|
124 |
+
"content": "1",
|
125 |
"lstrip": false,
|
126 |
"normalized": true,
|
127 |
"rstrip": false,
|
|
|
129 |
"special": false
|
130 |
},
|
131 |
"91": {
|
132 |
+
"content": "ẽ",
|
133 |
"lstrip": false,
|
134 |
"normalized": true,
|
135 |
"rstrip": false,
|
|
|
137 |
"special": false
|
138 |
},
|
139 |
"92": {
|
140 |
+
"content": "5",
|
141 |
"lstrip": false,
|
142 |
"normalized": true,
|
143 |
"rstrip": false,
|
|
|
145 |
"special": false
|
146 |
},
|
147 |
"93": {
|
148 |
+
"content": "õ",
|
149 |
"lstrip": false,
|
150 |
"normalized": true,
|
151 |
"rstrip": false,
|
|
|
153 |
"special": false
|
154 |
},
|
155 |
"94": {
|
156 |
+
"content": "2",
|
157 |
"lstrip": false,
|
158 |
"normalized": true,
|
159 |
"rstrip": false,
|
|
|
161 |
"special": false
|
162 |
},
|
163 |
"95": {
|
164 |
+
"content": "8",
|
165 |
"lstrip": false,
|
166 |
"normalized": true,
|
167 |
"rstrip": false,
|
|
|
169 |
"special": false
|
170 |
},
|
171 |
"96": {
|
172 |
+
"content": "ụ",
|
173 |
"lstrip": false,
|
174 |
"normalized": true,
|
175 |
"rstrip": false,
|
|
|
177 |
"special": false
|
178 |
},
|
179 |
"97": {
|
180 |
+
"content": "ằ",
|
181 |
"lstrip": false,
|
182 |
"normalized": true,
|
183 |
"rstrip": false,
|
|
|
185 |
"special": false
|
186 |
},
|
187 |
"98": {
|
188 |
+
"content": "ờ",
|
189 |
"lstrip": false,
|
190 |
"normalized": true,
|
191 |
"rstrip": false,
|
|
|
193 |
"special": false
|
194 |
},
|
195 |
"99": {
|
196 |
+
"content": "ỉ",
|
197 |
"lstrip": false,
|
198 |
"normalized": true,
|
199 |
"rstrip": false,
|
|
|
201 |
"special": false
|
202 |
},
|
203 |
"100": {
|
204 |
+
"content": " ",
|
205 |
"lstrip": false,
|
206 |
"normalized": true,
|
207 |
"rstrip": false,
|
|
|
209 |
"special": false
|
210 |
},
|
211 |
"101": {
|
212 |
+
"content": "ồ",
|
213 |
"lstrip": false,
|
214 |
"normalized": true,
|
215 |
"rstrip": false,
|
|
|
217 |
"special": false
|
218 |
},
|
219 |
"102": {
|
220 |
+
"content": "ắ",
|
221 |
"lstrip": false,
|
222 |
"normalized": true,
|
223 |
"rstrip": false,
|
|
|
225 |
"special": false
|
226 |
},
|
227 |
"103": {
|
228 |
+
"content": "ó",
|
229 |
"lstrip": false,
|
230 |
"normalized": true,
|
231 |
"rstrip": false,
|
|
|
233 |
"special": false
|
234 |
},
|
235 |
"104": {
|
236 |
+
"content": "ẳ",
|
237 |
"lstrip": false,
|
238 |
"normalized": true,
|
239 |
"rstrip": false,
|
|
|
241 |
"special": false
|
242 |
},
|
243 |
"105": {
|
244 |
+
"content": "ố",
|
245 |
"lstrip": false,
|
246 |
"normalized": true,
|
247 |
"rstrip": false,
|
|
|
249 |
"special": false
|
250 |
},
|
251 |
"106": {
|
252 |
+
"content": "ả",
|
253 |
"lstrip": false,
|
254 |
"normalized": true,
|
255 |
"rstrip": false,
|
|
|
257 |
"special": false
|
258 |
},
|
259 |
"107": {
|
260 |
+
"content": "%",
|
261 |
"lstrip": false,
|
262 |
"normalized": true,
|
263 |
"rstrip": false,
|
|
|
265 |
"special": false
|
266 |
},
|
267 |
"108": {
|
268 |
+
"content": "ạ",
|
269 |
"lstrip": false,
|
270 |
"normalized": true,
|
271 |
"rstrip": false,
|
|
|
273 |
"special": false
|
274 |
},
|
275 |
"109": {
|
276 |
+
"content": "ỷ",
|
277 |
"lstrip": false,
|
278 |
"normalized": true,
|
279 |
"rstrip": false,
|
|
|
281 |
"special": false
|
282 |
},
|
283 |
"110": {
|
284 |
+
"content": "ỡ",
|
285 |
"lstrip": false,
|
286 |
"normalized": true,
|
287 |
"rstrip": false,
|
|
|
289 |
"special": false
|
290 |
},
|
291 |
"111": {
|
292 |
+
"content": "Ừ",
|
293 |
"lstrip": false,
|
294 |
"normalized": true,
|
295 |
"rstrip": false,
|
|
|
297 |
"special": false
|
298 |
},
|
299 |
"112": {
|
300 |
+
"content": "ề",
|
301 |
"lstrip": false,
|
302 |
"normalized": true,
|
303 |
"rstrip": false,
|
|
|
305 |
"special": false
|
306 |
},
|
307 |
"113": {
|
308 |
+
"content": "â",
|
309 |
"lstrip": false,
|
310 |
"normalized": true,
|
311 |
"rstrip": false,
|
|
|
313 |
"special": false
|
314 |
},
|
315 |
"114": {
|
316 |
+
"content": "ị",
|
317 |
"lstrip": false,
|
318 |
"normalized": true,
|
319 |
"rstrip": false,
|
|
|
321 |
"special": false
|
322 |
},
|
323 |
"115": {
|
324 |
+
"content": "ễ",
|
325 |
"lstrip": false,
|
326 |
"normalized": true,
|
327 |
"rstrip": false,
|
|
|
329 |
"special": false
|
330 |
},
|
331 |
"116": {
|
332 |
+
"content": "Á",
|
333 |
"lstrip": false,
|
334 |
"normalized": true,
|
335 |
"rstrip": false,
|
|
|
345 |
"special": false
|
346 |
},
|
347 |
"118": {
|
348 |
+
"content": "ử",
|
349 |
"lstrip": false,
|
350 |
"normalized": true,
|
351 |
"rstrip": false,
|
|
|
353 |
"special": false
|
354 |
},
|
355 |
"119": {
|
356 |
+
"content": "4",
|
357 |
"lstrip": false,
|
358 |
"normalized": true,
|
359 |
"rstrip": false,
|
|
|
361 |
"special": false
|
362 |
},
|
363 |
"120": {
|
364 |
+
"content": "ỹ",
|
365 |
"lstrip": false,
|
366 |
"normalized": true,
|
367 |
"rstrip": false,
|
|
|
369 |
"special": false
|
370 |
},
|
371 |
"121": {
|
372 |
+
"content": "ù",
|
373 |
"lstrip": false,
|
374 |
"normalized": true,
|
375 |
"rstrip": false,
|
|
|
377 |
"special": false
|
378 |
},
|
379 |
"122": {
|
380 |
+
"content": "ú",
|
381 |
"lstrip": false,
|
382 |
"normalized": true,
|
383 |
"rstrip": false,
|
|
|
385 |
"special": false
|
386 |
},
|
387 |
"123": {
|
388 |
+
"content": "á",
|
389 |
"lstrip": false,
|
390 |
"normalized": true,
|
391 |
"rstrip": false,
|
|
|
393 |
"special": false
|
394 |
},
|
395 |
"124": {
|
396 |
+
"content": "è",
|
397 |
"lstrip": false,
|
398 |
"normalized": true,
|
399 |
"rstrip": false,
|
|
|
401 |
"special": false
|
402 |
},
|
403 |
"125": {
|
404 |
+
"content": "Ê",
|
405 |
"lstrip": false,
|
406 |
"normalized": true,
|
407 |
"rstrip": false,
|
|
|
409 |
"special": false
|
410 |
},
|
411 |
"126": {
|
412 |
+
"content": "ì",
|
413 |
"lstrip": false,
|
414 |
"normalized": true,
|
415 |
"rstrip": false,
|
|
|
417 |
"special": false
|
418 |
},
|
419 |
"127": {
|
420 |
+
"content": "ổ",
|
421 |
"lstrip": false,
|
422 |
"normalized": true,
|
423 |
"rstrip": false,
|
|
|
425 |
"special": false
|
426 |
},
|
427 |
"128": {
|
428 |
+
"content": "Đ",
|
429 |
"lstrip": false,
|
430 |
"normalized": true,
|
431 |
"rstrip": false,
|
|
|
433 |
"special": false
|
434 |
},
|
435 |
"129": {
|
436 |
+
"content": "ọ",
|
437 |
"lstrip": false,
|
438 |
"normalized": true,
|
439 |
"rstrip": false,
|
|
|
441 |
"special": false
|
442 |
},
|
443 |
"130": {
|
444 |
+
"content": "ỗ",
|
445 |
"lstrip": false,
|
446 |
"normalized": true,
|
447 |
"rstrip": false,
|
|
|
449 |
"special": false
|
450 |
},
|
451 |
"131": {
|
452 |
+
"content": "3",
|
453 |
"lstrip": false,
|
454 |
"normalized": true,
|
455 |
"rstrip": false,
|
|
|
457 |
"special": false
|
458 |
},
|
459 |
"132": {
|
460 |
+
"content": "0",
|
461 |
"lstrip": false,
|
462 |
"normalized": true,
|
463 |
"rstrip": false,
|
|
|
465 |
"special": false
|
466 |
},
|
467 |
"133": {
|
468 |
+
"content": "ầ",
|
469 |
"lstrip": false,
|
470 |
"normalized": true,
|
471 |
"rstrip": false,
|
|
|
473 |
"special": false
|
474 |
},
|
475 |
"134": {
|
476 |
+
"content": "À",
|
477 |
"lstrip": false,
|
478 |
"normalized": true,
|
479 |
"rstrip": false,
|
|
|
481 |
"special": false
|
482 |
},
|
483 |
"135": {
|
484 |
+
"content": "Ô",
|
485 |
"lstrip": false,
|
486 |
"normalized": true,
|
487 |
"rstrip": false,
|
|
|
489 |
"special": false
|
490 |
},
|
491 |
"136": {
|
492 |
+
"content": "ĩ",
|
493 |
"lstrip": false,
|
494 |
"normalized": true,
|
495 |
"rstrip": false,
|
|
|
497 |
"special": false
|
498 |
},
|
499 |
"137": {
|
500 |
+
"content": "ế",
|
501 |
"lstrip": false,
|
502 |
"normalized": true,
|
503 |
"rstrip": false,
|
|
|
505 |
"special": false
|
506 |
},
|
507 |
"138": {
|
508 |
+
"content": "ơ",
|
509 |
"lstrip": false,
|
510 |
"normalized": true,
|
511 |
"rstrip": false,
|
|
|
513 |
"special": false
|
514 |
},
|
515 |
"139": {
|
516 |
+
"content": "ò",
|
517 |
"lstrip": false,
|
518 |
"normalized": true,
|
519 |
"rstrip": false,
|
|
|
521 |
"special": false
|
522 |
},
|
523 |
"140": {
|
524 |
+
"content": "ư",
|
525 |
"lstrip": false,
|
526 |
"normalized": true,
|
527 |
"rstrip": false,
|
|
|
529 |
"special": false
|
530 |
},
|
531 |
"141": {
|
532 |
+
"content": "ặ",
|
533 |
"lstrip": false,
|
534 |
"normalized": true,
|
535 |
"rstrip": false,
|
|
|
537 |
"special": false
|
538 |
},
|
539 |
"142": {
|
540 |
+
"content": "ứ",
|
541 |
"lstrip": false,
|
542 |
"normalized": true,
|
543 |
"rstrip": false,
|
|
|
545 |
"special": false
|
546 |
},
|
547 |
"143": {
|
548 |
+
"content": "à",
|
549 |
"lstrip": false,
|
550 |
"normalized": true,
|
551 |
"rstrip": false,
|
|
|
553 |
"special": false
|
554 |
},
|
555 |
"144": {
|
556 |
+
"content": "ẫ",
|
557 |
"lstrip": false,
|
558 |
"normalized": true,
|
559 |
"rstrip": false,
|
|
|
561 |
"special": false
|
562 |
},
|
563 |
"145": {
|
564 |
+
"content": "ợ",
|
565 |
"lstrip": false,
|
566 |
"normalized": true,
|
567 |
"rstrip": false,
|
|
|
569 |
"special": false
|
570 |
},
|
571 |
"146": {
|
572 |
+
"content": "ủ",
|
573 |
"lstrip": false,
|
574 |
"normalized": true,
|
575 |
"rstrip": false,
|
|
|
577 |
"special": false
|
578 |
},
|
579 |
"147": {
|
580 |
+
"content": "ậ",
|
581 |
"lstrip": false,
|
582 |
"normalized": true,
|
583 |
"rstrip": false,
|
|
|
585 |
"special": false
|
586 |
},
|
587 |
"148": {
|
588 |
+
"content": "Ý",
|
589 |
"lstrip": false,
|
590 |
"normalized": true,
|
591 |
"rstrip": false,
|
|
|
593 |
"special": false
|
594 |
},
|
595 |
"149": {
|
596 |
+
"content": "ấ",
|
597 |
"lstrip": false,
|
598 |
"normalized": true,
|
599 |
"rstrip": false,
|
|
|
601 |
"special": false
|
602 |
},
|
603 |
"150": {
|
604 |
+
"content": "ộ",
|
605 |
"lstrip": false,
|
606 |
"normalized": true,
|
607 |
"rstrip": false,
|
|
|
609 |
"special": false
|
610 |
},
|
611 |
"151": {
|
612 |
+
"content": "9",
|
613 |
"lstrip": false,
|
614 |
"normalized": true,
|
615 |
"rstrip": false,
|
|
|
617 |
"special": false
|
618 |
},
|
619 |
"152": {
|
620 |
+
"content": "ẻ",
|
621 |
"lstrip": false,
|
622 |
"normalized": true,
|
623 |
"rstrip": false,
|
|
|
625 |
"special": false
|
626 |
},
|
627 |
"153": {
|
628 |
+
"content": "ô",
|
629 |
"lstrip": false,
|
630 |
"normalized": true,
|
631 |
"rstrip": false,
|
|
|
633 |
"special": false
|
634 |
},
|
635 |
"154": {
|
636 |
+
"content": "í",
|
637 |
"lstrip": false,
|
638 |
"normalized": true,
|
639 |
"rstrip": false,
|
|
|
641 |
"special": false
|
642 |
},
|
643 |
"155": {
|
644 |
+
"content": "ở",
|
645 |
"lstrip": false,
|
646 |
"normalized": true,
|
647 |
"rstrip": false,
|
|
|
649 |
"special": false
|
650 |
},
|
651 |
"156": {
|
652 |
+
"content": "ữ",
|
653 |
"lstrip": false,
|
654 |
"normalized": true,
|
655 |
"rstrip": false,
|
|
|
657 |
"special": false
|
658 |
},
|
659 |
"157": {
|
660 |
+
"content": "ừ",
|
661 |
"lstrip": false,
|
662 |
"normalized": true,
|
663 |
"rstrip": false,
|
|
|
665 |
"special": false
|
666 |
},
|
667 |
"158": {
|
668 |
+
"content": "ự",
|
669 |
"lstrip": false,
|
670 |
"normalized": true,
|
671 |
"rstrip": false,
|
|
|
673 |
"special": false
|
674 |
},
|
675 |
"159": {
|
676 |
+
"content": "ẩ",
|
677 |
"lstrip": false,
|
678 |
"normalized": true,
|
679 |
"rstrip": false,
|
|
|
681 |
"special": false
|
682 |
},
|
683 |
"160": {
|
684 |
+
"content": "ớ",
|
685 |
"lstrip": false,
|
686 |
"normalized": true,
|
687 |
"rstrip": false,
|
|
|
689 |
"special": false
|
690 |
},
|
691 |
"161": {
|
692 |
+
"content": "ũ",
|
693 |
"lstrip": false,
|
694 |
"normalized": true,
|
695 |
"rstrip": false,
|
|
|
697 |
"special": false
|
698 |
},
|
699 |
"162": {
|
700 |
+
"content": "ý",
|
701 |
"lstrip": false,
|
702 |
"normalized": true,
|
703 |
"rstrip": false,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78b0061a34ee2312a0b98121895a636038c39778697b39d269d938d612598e38
|
3 |
size 5368
|