codebyzeb commited on
Commit
57b71d2
·
verified ·
1 Parent(s): d7e180f

Upload folder using huggingface_hub

Browse files
fw57M_Entropy_thresholdBX_600/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|padding|>",
5
+ "unk_token": "<|unk|>"
6
+ }
fw57M_Entropy_thresholdBX_600/stats.csv ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ num_moves,vocab_size,unique_segments,threshold
2
+ 0,515,1,5.133828295811327e-08
3
+ 1000,516,22,9.790553576749517e-07
4
+ 2000,516,25,1.4309060816231067e-06
5
+ 3000,516,27,1.8229197848995682e-06
6
+ 4000,517,30,2.1990540517435875e-06
7
+ 5000,517,34,2.5248320980608696e-06
8
+ 6000,517,37,2.8365827802190324e-06
9
+ 7000,517,39,3.127169520666939e-06
10
+ 8000,517,42,3.4406789382046554e-06
11
+ 9000,517,44,3.7212562347122002e-06
12
+ 10000,517,46,4.012302269984502e-06
13
+ 11000,517,47,4.296648512536194e-06
14
+ 12000,517,49,4.568334588839207e-06
15
+ 13000,518,54,4.853022801398765e-06
16
+ 14000,518,58,5.109339326736517e-06
17
+ 15000,518,65,5.373932253860403e-06
18
+ 16000,518,67,5.649672857543919e-06
19
+ 17000,518,69,5.914777375437552e-06
20
+ 18000,518,73,6.172143912408501e-06
21
+ 19000,519,76,6.424897492252057e-06
22
+ 20000,520,77,6.700956419081194e-06
23
+ 21000,520,81,6.9617381086573005e-06
24
+ 22000,520,84,7.22233698979835e-06
25
+ 23000,521,86,7.478172392438864e-06
26
+ 24000,521,92,7.740409273537807e-06
27
+ 25000,521,94,8.001956302905455e-06
28
+ 26000,521,98,8.264463758678176e-06
29
+ 27000,522,104,8.528708349331282e-06
30
+ 28000,522,107,8.773720765020698e-06
31
+ 29000,522,109,9.04225635167677e-06
32
+ 30000,523,113,9.290170055464841e-06
33
+ 31000,523,117,9.528370355837978e-06
34
+ 32000,524,118,9.79736796580255e-06
35
+ 33000,525,122,1.0070482858282048e-05
36
+ 34000,525,127,1.0339319487684406e-05
37
+ 35000,525,129,1.0614803613862023e-05
38
+ 36000,526,133,1.0890100384131074e-05
39
+ 37000,527,135,1.1162222108396236e-05
40
+ 38000,527,139,1.1431737220846117e-05
41
+ 39000,527,139,1.1706975783454254e-05
42
+ 40000,528,143,1.1987172001681756e-05
43
+ 41000,529,148,1.224808602273697e-05
44
+ 42000,529,150,1.2501597666414455e-05
45
+ 43000,529,152,1.2784775208274368e-05
46
+ 44000,529,154,1.307702677877387e-05
47
+ 45000,530,154,1.3359001059143338e-05
48
+ 46000,531,157,1.3647608284372836e-05
49
+ 47000,532,158,1.3921197023591958e-05
50
+ 48000,533,161,1.4208838365448173e-05
51
+ 49000,533,162,1.4507069863611832e-05
52
+ 50000,533,166,1.4814748283242807e-05
53
+ 51000,534,168,1.5173626707110088e-05
54
+ 52000,534,170,1.5574130884488113e-05
55
+ 53000,535,173,1.6095349565148354e-05
56
+ 54000,535,174,1.6789324945420958e-05
57
+ 55000,536,178,1.7530710465507582e-05
58
+ 56000,536,182,1.807898297556676e-05
59
+ 57000,536,186,1.855349910329096e-05
60
+ 58000,537,189,1.89148177014431e-05
61
+ 59000,541,192,1.9255410734331235e-05
62
+ 60000,541,196,1.9606726709753275e-05
63
+ 61000,541,198,1.993944897549227e-05
64
+ 62000,543,202,2.026474612648599e-05
65
+ 63000,543,204,2.057795245491434e-05
66
+ 64000,543,208,2.0897583453916013e-05
67
+ 65000,544,210,2.1221829229034483e-05
68
+ 66000,545,212,2.1535339328693226e-05
69
+ 67000,548,219,2.1876883693039417e-05
70
+ 68000,550,220,2.2192627511685714e-05
71
+ 69000,553,224,2.2512333089252934e-05
72
+ 70000,554,225,2.281865272379946e-05
73
+ 71000,554,228,2.3127340682549402e-05
74
+ 72000,554,231,2.3458222131012008e-05
75
+ 73000,555,237,2.3790689738234505e-05
76
+ 74000,558,238,2.412626963632647e-05
77
+ 75000,559,239,2.4468832634738646e-05
78
+ 76000,560,240,2.481048068148084e-05
79
+ 77000,561,242,2.5139239369309507e-05
80
+ 78000,561,246,2.5478828320046887e-05
81
+ 79000,561,249,2.5810599254327826e-05
82
+ 80000,562,252,2.6150766643695533e-05
83
+ 81000,563,255,2.6495927158975974e-05
84
+ 82000,564,256,2.6845029424293898e-05
85
+ 83000,564,259,2.7201735065318644e-05
86
+ 84000,564,263,2.755965215328615e-05
87
+ 85000,564,267,2.7887075702892616e-05
88
+ 86000,566,272,2.823129943863023e-05
89
+ 87000,566,274,2.858073821698781e-05
90
+ 88000,567,275,2.8935739464941435e-05
91
+ 89000,567,280,2.9296392312971875e-05
92
+ 90000,568,286,2.9659753636224195e-05
93
+ 91000,568,292,3.002668745466508e-05
94
+ 92000,571,295,3.0397197406273335e-05
95
+ 93000,571,299,3.074545384151861e-05
96
+ 94000,571,301,3.1101779313758016e-05
97
+ 95000,571,305,3.149575786665082e-05
98
+ 96000,571,307,3.189174094586633e-05
99
+ 97000,571,309,3.22468149533961e-05
100
+ 98000,573,314,3.26372537529096e-05
101
+ 99000,575,319,3.3024651202140376e-05
102
+ 100000,575,322,3.339877730468288e-05
103
+ 101000,576,330,3.377669054316357e-05
104
+ 102000,576,334,3.417441257624887e-05
105
+ 103000,576,339,3.456857302808203e-05
106
+ 104000,576,344,3.496912540867925e-05
107
+ 105000,576,349,3.5385990486247465e-05
108
+ 106000,577,354,3.575959999579936e-05
109
+ 107000,577,358,3.61450802301988e-05
110
+ 108000,578,359,3.653268504422158e-05
111
+ 109000,579,363,3.6942012229701504e-05
112
+ 110000,581,370,3.730935713974759e-05
113
+ 111000,582,373,3.769703835132532e-05
114
+ 112000,584,378,3.8120309909572825e-05
115
+ 113000,585,383,3.853967791656032e-05
116
+ 114000,585,386,3.8975511415628716e-05
117
+ 115000,588,393,3.93725567846559e-05
118
+ 116000,588,397,3.9807622670196e-05
119
+ 117000,589,402,4.022541907033883e-05
120
+ 118000,589,405,4.067840927746147e-05
121
+ 119000,593,408,4.113887916901149e-05
122
+ 120000,594,411,4.1620303818490356e-05
123
+ 121000,596,414,4.212183193885721e-05
124
+ 122000,596,418,4.26527694799006e-05
125
+ 123000,598,421,4.322654058341868e-05
126
+ 124000,598,422,4.3803440348710865e-05
127
+ 125000,598,426,4.446713501238264e-05
128
+ 126000,598,431,4.5173615944804624e-05
129
+ 127000,600,435,4.5849425077904016e-05
fw57M_Entropy_thresholdBX_600/tokenizer.json ADDED
@@ -0,0 +1,670 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|padding|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|endoftext|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 514,
26
+ "content": "<|unk|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Sequence",
36
+ "normalizers": [
37
+ {
38
+ "type": "NFD"
39
+ }
40
+ ]
41
+ },
42
+ "pre_tokenizer": {
43
+ "type": "Split",
44
+ "pattern": {
45
+ "Regex": "^$"
46
+ },
47
+ "behavior": "Contiguous",
48
+ "invert": false
49
+ },
50
+ "post_processor": {
51
+ "type": "ByteLevel",
52
+ "add_prefix_space": true,
53
+ "trim_offsets": true,
54
+ "use_regex": true
55
+ },
56
+ "decoder": {
57
+ "type": "ByteLevel",
58
+ "add_prefix_space": true,
59
+ "trim_offsets": true,
60
+ "use_regex": true
61
+ },
62
+ "model": {
63
+ "type": "WordPiece",
64
+ "unk_token": "<|unk|>",
65
+ "continuing_subword_prefix": "##",
66
+ "max_input_chars_per_word": 100,
67
+ "vocab": {
68
+ "<|padding|>": 0,
69
+ "<|endoftext|>": 1,
70
+ "!": 2,
71
+ "\"": 3,
72
+ "#": 4,
73
+ "$": 5,
74
+ "%": 6,
75
+ "&": 7,
76
+ "'": 8,
77
+ "(": 9,
78
+ ")": 10,
79
+ "*": 11,
80
+ "+": 12,
81
+ ",": 13,
82
+ "-": 14,
83
+ ".": 15,
84
+ "/": 16,
85
+ "0": 17,
86
+ "1": 18,
87
+ "2": 19,
88
+ "3": 20,
89
+ "4": 21,
90
+ "5": 22,
91
+ "6": 23,
92
+ "7": 24,
93
+ "8": 25,
94
+ "9": 26,
95
+ ":": 27,
96
+ ";": 28,
97
+ "<": 29,
98
+ "=": 30,
99
+ ">": 31,
100
+ "?": 32,
101
+ "@": 33,
102
+ "A": 34,
103
+ "B": 35,
104
+ "C": 36,
105
+ "D": 37,
106
+ "E": 38,
107
+ "F": 39,
108
+ "G": 40,
109
+ "H": 41,
110
+ "I": 42,
111
+ "J": 43,
112
+ "K": 44,
113
+ "L": 45,
114
+ "M": 46,
115
+ "N": 47,
116
+ "O": 48,
117
+ "P": 49,
118
+ "Q": 50,
119
+ "R": 51,
120
+ "S": 52,
121
+ "T": 53,
122
+ "U": 54,
123
+ "V": 55,
124
+ "W": 56,
125
+ "X": 57,
126
+ "Y": 58,
127
+ "Z": 59,
128
+ "[": 60,
129
+ "\\": 61,
130
+ "]": 62,
131
+ "^": 63,
132
+ "_": 64,
133
+ "`": 65,
134
+ "a": 66,
135
+ "b": 67,
136
+ "c": 68,
137
+ "d": 69,
138
+ "e": 70,
139
+ "f": 71,
140
+ "g": 72,
141
+ "h": 73,
142
+ "i": 74,
143
+ "j": 75,
144
+ "k": 76,
145
+ "l": 77,
146
+ "m": 78,
147
+ "n": 79,
148
+ "o": 80,
149
+ "p": 81,
150
+ "q": 82,
151
+ "r": 83,
152
+ "s": 84,
153
+ "t": 85,
154
+ "u": 86,
155
+ "v": 87,
156
+ "w": 88,
157
+ "x": 89,
158
+ "y": 90,
159
+ "z": 91,
160
+ "{": 92,
161
+ "|": 93,
162
+ "}": 94,
163
+ "~": 95,
164
+ "¡": 96,
165
+ "¢": 97,
166
+ "£": 98,
167
+ "¤": 99,
168
+ "¥": 100,
169
+ "¦": 101,
170
+ "§": 102,
171
+ "¨": 103,
172
+ "©": 104,
173
+ "ª": 105,
174
+ "«": 106,
175
+ "¬": 107,
176
+ "®": 108,
177
+ "¯": 109,
178
+ "°": 110,
179
+ "±": 111,
180
+ "²": 112,
181
+ "³": 113,
182
+ "´": 114,
183
+ "µ": 115,
184
+ "¶": 116,
185
+ "·": 117,
186
+ "¸": 118,
187
+ "¹": 119,
188
+ "º": 120,
189
+ "»": 121,
190
+ "¼": 122,
191
+ "½": 123,
192
+ "¾": 124,
193
+ "¿": 125,
194
+ "À": 126,
195
+ "Á": 127,
196
+ "Â": 128,
197
+ "Ã": 129,
198
+ "Ä": 130,
199
+ "Å": 131,
200
+ "Æ": 132,
201
+ "Ç": 133,
202
+ "È": 134,
203
+ "É": 135,
204
+ "Ê": 136,
205
+ "Ë": 137,
206
+ "Ì": 138,
207
+ "Í": 139,
208
+ "Î": 140,
209
+ "Ï": 141,
210
+ "Ð": 142,
211
+ "Ñ": 143,
212
+ "Ò": 144,
213
+ "Ó": 145,
214
+ "Ô": 146,
215
+ "Õ": 147,
216
+ "Ö": 148,
217
+ "×": 149,
218
+ "Ø": 150,
219
+ "Ù": 151,
220
+ "Ú": 152,
221
+ "Û": 153,
222
+ "Ü": 154,
223
+ "Ý": 155,
224
+ "Þ": 156,
225
+ "ß": 157,
226
+ "à": 158,
227
+ "á": 159,
228
+ "â": 160,
229
+ "ã": 161,
230
+ "ä": 162,
231
+ "å": 163,
232
+ "æ": 164,
233
+ "ç": 165,
234
+ "è": 166,
235
+ "é": 167,
236
+ "ê": 168,
237
+ "ë": 169,
238
+ "ì": 170,
239
+ "í": 171,
240
+ "î": 172,
241
+ "ï": 173,
242
+ "ð": 174,
243
+ "ñ": 175,
244
+ "ò": 176,
245
+ "ó": 177,
246
+ "ô": 178,
247
+ "õ": 179,
248
+ "ö": 180,
249
+ "÷": 181,
250
+ "ø": 182,
251
+ "ù": 183,
252
+ "ú": 184,
253
+ "û": 185,
254
+ "ü": 186,
255
+ "ý": 187,
256
+ "þ": 188,
257
+ "ÿ": 189,
258
+ "Ā": 190,
259
+ "ā": 191,
260
+ "Ă": 192,
261
+ "ă": 193,
262
+ "Ą": 194,
263
+ "ą": 195,
264
+ "Ć": 196,
265
+ "ć": 197,
266
+ "Ĉ": 198,
267
+ "ĉ": 199,
268
+ "Ċ": 200,
269
+ "ċ": 201,
270
+ "Č": 202,
271
+ "č": 203,
272
+ "Ď": 204,
273
+ "ď": 205,
274
+ "Đ": 206,
275
+ "đ": 207,
276
+ "Ē": 208,
277
+ "ē": 209,
278
+ "Ĕ": 210,
279
+ "ĕ": 211,
280
+ "Ė": 212,
281
+ "ė": 213,
282
+ "Ę": 214,
283
+ "ę": 215,
284
+ "Ě": 216,
285
+ "ě": 217,
286
+ "Ĝ": 218,
287
+ "ĝ": 219,
288
+ "Ğ": 220,
289
+ "ğ": 221,
290
+ "Ġ": 222,
291
+ "ġ": 223,
292
+ "Ģ": 224,
293
+ "ģ": 225,
294
+ "Ĥ": 226,
295
+ "ĥ": 227,
296
+ "Ħ": 228,
297
+ "ħ": 229,
298
+ "Ĩ": 230,
299
+ "ĩ": 231,
300
+ "Ī": 232,
301
+ "ī": 233,
302
+ "Ĭ": 234,
303
+ "ĭ": 235,
304
+ "Į": 236,
305
+ "į": 237,
306
+ "İ": 238,
307
+ "ı": 239,
308
+ "IJ": 240,
309
+ "ij": 241,
310
+ "Ĵ": 242,
311
+ "ĵ": 243,
312
+ "Ķ": 244,
313
+ "ķ": 245,
314
+ "ĸ": 246,
315
+ "Ĺ": 247,
316
+ "ĺ": 248,
317
+ "Ļ": 249,
318
+ "ļ": 250,
319
+ "Ľ": 251,
320
+ "ľ": 252,
321
+ "Ŀ": 253,
322
+ "ŀ": 254,
323
+ "Ł": 255,
324
+ "ł": 256,
325
+ "Ń": 257,
326
+ "##Q": 258,
327
+ "##9": 259,
328
+ "##¨": 260,
329
+ "##Y": 261,
330
+ "##E": 262,
331
+ "##č": 263,
332
+ "##®": 264,
333
+ "##Ċ": 265,
334
+ "##h": 266,
335
+ "##ę": 267,
336
+ "##Ě": 268,
337
+ "##ç": 269,
338
+ "##2": 270,
339
+ "##¬": 271,
340
+ "##Ĺ": 272,
341
+ "##Z": 273,
342
+ "##C": 274,
343
+ "##-": 275,
344
+ "##Ĥ": 276,
345
+ "##=": 277,
346
+ "##f": 278,
347
+ "##IJ": 279,
348
+ "##Ĝ": 280,
349
+ "##^": 281,
350
+ "##H": 282,
351
+ "##w": 283,
352
+ "##â": 284,
353
+ "##ô": 285,
354
+ "##\\": 286,
355
+ "##ĝ": 287,
356
+ "##O": 288,
357
+ "##Ľ": 289,
358
+ "##V": 290,
359
+ "##đ": 291,
360
+ "##?": 292,
361
+ "##i": 293,
362
+ "##Ó": 294,
363
+ "##Õ": 295,
364
+ "##è": 296,
365
+ "##þ": 297,
366
+ "##7": 298,
367
+ "##¢": 299,
368
+ "##Ã": 300,
369
+ "##Ā": 301,
370
+ "##Ģ": 302,
371
+ "##\"": 303,
372
+ "##x": 304,
373
+ "##_": 305,
374
+ "##Ë": 306,
375
+ "##ā": 307,
376
+ "##Â": 308,
377
+ "##ģ": 309,
378
+ "##Ô": 310,
379
+ "##ĩ": 311,
380
+ "##>": 312,
381
+ "##å": 313,
382
+ "##%": 314,
383
+ "##ü": 315,
384
+ "##÷": 316,
385
+ "##Ø": 317,
386
+ "##Ì": 318,
387
+ "##F": 319,
388
+ "##4": 320,
389
+ "##¶": 321,
390
+ "##©": 322,
391
+ "##¥": 323,
392
+ "##Ĉ": 324,
393
+ "##c": 325,
394
+ "##]": 326,
395
+ "##)": 327,
396
+ "##ħ": 328,
397
+ "##Ĕ": 329,
398
+ "##Į": 330,
399
+ "##ľ": 331,
400
+ "##º": 332,
401
+ "##Î": 333,
402
+ "##Ð": 334,
403
+ "##(": 335,
404
+ "##|": 336,
405
+ "##Ö": 337,
406
+ "##ì": 338,
407
+ "##ú": 339,
408
+ "##ª": 340,
409
+ "##Ú": 341,
410
+ "##Č": 342,
411
+ "##.": 343,
412
+ "##¹": 344,
413
+ "##½": 345,
414
+ "##Ŀ": 346,
415
+ "##;": 347,
416
+ "##í": 348,
417
+ "##´": 349,
418
+ "##b": 350,
419
+ "##¤": 351,
420
+ "##À": 352,
421
+ "##Ï": 353,
422
+ "##G": 354,
423
+ "##P": 355,
424
+ "##¦": 356,
425
+ "##ï": 357,
426
+ "##Ć": 358,
427
+ "##ī": 359,
428
+ "##Ą": 360,
429
+ "##R": 361,
430
+ "##ă": 362,
431
+ "##s": 363,
432
+ "##3": 364,
433
+ "##I": 365,
434
+ "##±": 366,
435
+ "##İ": 367,
436
+ "##£": 368,
437
+ "##Ă": 369,
438
+ "##0": 370,
439
+ "##Đ": 371,
440
+ "##ł": 372,
441
+ "##ĥ": 373,
442
+ "##ó": 374,
443
+ "##õ": 375,
444
+ "##û": 376,
445
+ "##ķ": 377,
446
+ "##D": 378,
447
+ "##z": 379,
448
+ "##Ď": 380,
449
+ "##ĸ": 381,
450
+ "##¿": 382,
451
+ "##×": 383,
452
+ "##k": 384,
453
+ "##1": 385,
454
+ "##Þ": 386,
455
+ "##æ": 387,
456
+ "##$": 388,
457
+ "##A": 389,
458
+ "##ñ": 390,
459
+ "##Ĭ": 391,
460
+ "##³": 392,
461
+ "##:": 393,
462
+ "##Á": 394,
463
+ "##ď": 395,
464
+ "##§": 396,
465
+ "##ÿ": 397,
466
+ "##Ī": 398,
467
+ "##Ļ": 399,
468
+ "##B": 400,
469
+ "##Å": 401,
470
+ "##ġ": 402,
471
+ "##é": 403,
472
+ "##ı": 404,
473
+ "##ĺ": 405,
474
+ "##Ü": 406,
475
+ "##²": 407,
476
+ "##6": 408,
477
+ "##·": 409,
478
+ "##¸": 410,
479
+ "##ê": 411,
480
+ "##Ê": 412,
481
+ "##<": 413,
482
+ "##U": 414,
483
+ "##Ġ": 415,
484
+ "##e": 416,
485
+ "##5": 417,
486
+ "##!": 418,
487
+ "##ö": 419,
488
+ "##L": 420,
489
+ "##X": 421,
490
+ "##M": 422,
491
+ "##È": 423,
492
+ "##ĕ": 424,
493
+ "##Ė": 425,
494
+ "##Ķ": 426,
495
+ "##S": 427,
496
+ "##l": 428,
497
+ "##»": 429,
498
+ "##Ò": 430,
499
+ "##ù": 431,
500
+ "##ć": 432,
501
+ "##&": 433,
502
+ "##à": 434,
503
+ "##@": 435,
504
+ "##ý": 436,
505
+ "##Ä": 437,
506
+ "##p": 438,
507
+ "##î": 439,
508
+ "##ß": 440,
509
+ "##ø": 441,
510
+ "##t": 442,
511
+ "##µ": 443,
512
+ "##É": 444,
513
+ "##Ē": 445,
514
+ "##d": 446,
515
+ "##ċ": 447,
516
+ "##ě": 448,
517
+ "##Ł": 449,
518
+ "##8": 450,
519
+ "##ã": 451,
520
+ "##ĵ": 452,
521
+ "##Æ": 453,
522
+ "##¡": 454,
523
+ "##Ń": 455,
524
+ "##n": 456,
525
+ "##¼": 457,
526
+ "##j": 458,
527
+ "##Í": 459,
528
+ "##Ĩ": 460,
529
+ "##r": 461,
530
+ "##Ę": 462,
531
+ "##Ù": 463,
532
+ "##ij": 464,
533
+ "##Ğ": 465,
534
+ "##ğ": 466,
535
+ "##ą": 467,
536
+ "##ë": 468,
537
+ "##+": 469,
538
+ "##¯": 470,
539
+ "##ė": 471,
540
+ "##/": 472,
541
+ "##q": 473,
542
+ "##Ñ": 474,
543
+ "##Ħ": 475,
544
+ "##W": 476,
545
+ "##[": 477,
546
+ "##ä": 478,
547
+ "##Ç": 479,
548
+ "##ĭ": 480,
549
+ "##ļ": 481,
550
+ "##°": 482,
551
+ "##o": 483,
552
+ "##Ý": 484,
553
+ "##u": 485,
554
+ "##m": 486,
555
+ "##ē": 487,
556
+ "##g": 488,
557
+ "###": 489,
558
+ "##y": 490,
559
+ "##v": 491,
560
+ "##ŀ": 492,
561
+ "##¾": 493,
562
+ "##'": 494,
563
+ "##a": 495,
564
+ "##K": 496,
565
+ "##T": 497,
566
+ "##~": 498,
567
+ "##`": 499,
568
+ "##Û": 500,
569
+ "##{": 501,
570
+ "##«": 502,
571
+ "##á": 503,
572
+ "##N": 504,
573
+ "##ĉ": 505,
574
+ "##į": 506,
575
+ "##ð": 507,
576
+ "##Ĵ": 508,
577
+ "##}": 509,
578
+ "##*": 510,
579
+ "##J": 511,
580
+ "##ò": 512,
581
+ "##,": 513,
582
+ "<|unk|>": 514,
583
+ "##ng": 515,
584
+ "##�": 516,
585
+ "##er": 517,
586
+ "##nt": 518,
587
+ "##en": 519,
588
+ "##on": 520,
589
+ "##le": 521,
590
+ "##nd": 522,
591
+ "##her": 523,
592
+ "##ent": 524,
593
+ "##ss": 525,
594
+ "##gh": 526,
595
+ "##se": 527,
596
+ "##em": 528,
597
+ "##ur": 529,
598
+ "##he": 530,
599
+ "##in": 531,
600
+ "##es": 532,
601
+ "##th": 533,
602
+ "##ct": 534,
603
+ "##al": 535,
604
+ "##us": 536,
605
+ "##ar": 537,
606
+ "##ge": 538,
607
+ "##at": 539,
608
+ "##io": 540,
609
+ "##ve": 541,
610
+ "##ld": 542,
611
+ "##ce": 543,
612
+ "##ion": 544,
613
+ "##or": 545,
614
+ "##ple": 546,
615
+ "##ch": 547,
616
+ "##te": 548,
617
+ "##ll": 549,
618
+ "##me": 550,
619
+ "##ul": 551,
620
+ "##re": 552,
621
+ "##og": 553,
622
+ "##ti": 554,
623
+ "##an": 555,
624
+ "##ra": 556,
625
+ "##lt": 557,
626
+ "##rd": 558,
627
+ "##el": 559,
628
+ "##ht": 560,
629
+ "##st": 561,
630
+ "##ag": 562,
631
+ "##ut": 563,
632
+ "##pl": 564,
633
+ "##ue": 565,
634
+ "##ing": 566,
635
+ "##de": 567,
636
+ "##ow": 568,
637
+ "##rg": 569,
638
+ "##ect": 570,
639
+ "##is": 571,
640
+ "##et": 572,
641
+ "##tr": 573,
642
+ "##ay": 574,
643
+ "##ma": 575,
644
+ "##it": 576,
645
+ "##il": 577,
646
+ "##ri": 578,
647
+ "##dy": 579,
648
+ "##use": 580,
649
+ "##bl": 581,
650
+ "##ly": 582,
651
+ "##and": 583,
652
+ "##li": 584,
653
+ "##ne": 585,
654
+ "##ic": 586,
655
+ "##tem": 587,
656
+ "##ed": 588,
657
+ "##ess": 589,
658
+ "##as": 590,
659
+ "##ou": 591,
660
+ "##ec": 592,
661
+ "##om": 593,
662
+ "##uc": 594,
663
+ "##ke": 595,
664
+ "##ia": 596,
665
+ "##ud": 597,
666
+ "##sh": 598,
667
+ "##na": 599
668
+ }
669
+ }
670
+ }
fw57M_Entropy_thresholdBX_600/tokenizer_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|padding|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "514": {
21
+ "content": "<|unk|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "bos_token": "<|endoftext|>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "<|endoftext|>",
32
+ "extra_special_tokens": {},
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<|padding|>",
35
+ "tokenizer_class": "PreTrainedTokenizer",
36
+ "unk_token": "<|unk|>"
37
+ }
fw57M_Entropy_thresholdBX_600/vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"Q": 50, "9": 26, "\u00a8": 103, "Y": 58, "E": 38, "\u010d": 203, "\u00ae": 108, "\u010a": 200, "h": 73, "\u0119": 215, "\u011a": 216, "\u00e7": 165, "2": 19, "\u00ac": 107, "\u0139": 247, "Z": 59, "C": 36, "-": 14, "\u0124": 226, "=": 30, "f": 71, "\u0132": 240, "\u011c": 218, "^": 63, "H": 41, "w": 88, "\u00e2": 160, "\u00f4": 178, "\\": 61, "\u011d": 219, "O": 48, "\u013d": 251, "V": 55, "\u0111": 207, "?": 32, "i": 74, "\u00d3": 145, "\u00d5": 147, "\u00e8": 166, "\u00fe": 188, "7": 24, "\u00a2": 97, "\u00c3": 129, "\u0100": 190, "\u0122": 224, "\"": 3, "x": 89, "_": 64, "\u00cb": 137, "\u0101": 191, "\u00c2": 128, "\u0123": 225, "\u00d4": 146, "\u0129": 231, ">": 31, "\u00e5": 163, "%": 6, "\u00fc": 186, "\u00f7": 181, "\u00d8": 150, "\u00cc": 138, "F": 39, "4": 21, "\u00b6": 116, "\u00a9": 104, "\u00a5": 100, "\u0108": 198, "c": 68, "]": 62, ")": 10, "\u0127": 229, "\u0114": 210, "\u012e": 236, "\u013e": 252, "\u00ba": 120, "\u00ce": 140, "\u00d0": 142, "(": 9, "|": 93, "\u00d6": 148, "\u00ec": 170, "\u00fa": 184, "\u00aa": 105, "\u00da": 152, "\u010c": 202, ".": 15, "\u00b9": 119, "<|padding|>": 0, "\u00bd": 123, "\u013f": 253, ";": 28, "\u00ed": 171, "\u00b4": 114, "b": 67, "\u00a4": 99, "\u00c0": 126, "\u00cf": 141, "G": 40, "P": 49, "\u00a6": 101, "\u00ef": 173, "\u0106": 196, "\u012b": 233, "\u0104": 194, "R": 51, "\u0103": 193, "s": 84, "3": 20, "I": 42, "\u00b1": 111, "\u0130": 238, "\u00a3": 98, "\u0102": 192, "0": 17, "\u0110": 206, "\u0142": 256, "\u0125": 227, "\u00f3": 177, "\u00f5": 179, "\u00fb": 185, "\u0137": 245, "D": 37, "z": 91, "\u010e": 204, "\u0138": 246, "\u00bf": 125, "\u00d7": 149, "k": 76, "1": 18, "\u00de": 156, "\u00e6": 164, "$": 5, "A": 34, "\u00f1": 175, "\u012c": 234, "\u00b3": 113, ":": 27, "\u00c1": 127, "\u010f": 205, "\u00a7": 102, "\u00ff": 189, "\u012a": 232, "\u013b": 249, "B": 35, "\u00c5": 131, "\u0121": 223, "\u00e9": 167, "\u0131": 239, "\u013a": 248, "\u00dc": 154, "\u00b2": 112, "6": 23, "<|endoftext|>": 1, "\u00b7": 117, "\u00b8": 118, "\u00ea": 168, "\u00ca": 136, "<": 29, "U": 54, "\u0120": 222, "e": 70, "5": 22, "!": 2, "\u00f6": 180, "L": 45, "X": 57, "M": 46, "\u00c8": 134, "\u0115": 211, "\u0116": 212, "\u0136": 244, "S": 52, "l": 77, "\u00bb": 121, "\u00d2": 144, "\u00f9": 183, "\u0107": 197, "&": 7, "\u00e0": 158, "@": 33, "\u00fd": 187, "\u00c4": 130, "p": 81, "\u00ee": 172, "\u00df": 157, "\u00f8": 182, "t": 85, "\u00b5": 115, "\u00c9": 135, "\u0112": 208, "d": 69, "\u010b": 201, "\u011b": 217, "\u0141": 255, "8": 25, "\u00e3": 161, "\u0135": 243, "\u00c6": 132, "\u00a1": 96, "\u0143": 257, "n": 79, "\u00bc": 122, "j": 75, "\u00cd": 139, "\u0128": 230, "r": 83, "\u0118": 214, "\u00d9": 151, "\u0133": 241, "\u011e": 220, "\u011f": 221, "\u0105": 195, "\u00eb": 169, "+": 12, "\u00af": 109, "\u0117": 213, "/": 16, "q": 82, "\u00d1": 143, "\u0126": 228, "W": 56, "[": 60, "\u00e4": 162, "\u00c7": 133, "\u012d": 235, "\u013c": 250, "\u00b0": 110, "o": 80, "\u00dd": 155, "u": 86, "m": 78, "\u0113": 209, "g": 72, "#": 4, "y": 90, "v": 87, "\u0140": 254, "\u00be": 124, "'": 8, "a": 66, "K": 44, "T": 53, "~": 95, "`": 65, "\u00db": 153, "{": 92, "\u00ab": 106, "\u00e1": 159, "N": 47, "\u0109": 199, "\u012f": 237, "\u00f0": 174, "\u0134": 242, "}": 94, "*": 11, "J": 43, "\u00f2": 176, ",": 13, "##Q": 258, "##9": 259, "##\u00a8": 260, "##Y": 261, "##E": 262, "##\u010d": 263, "##\u00ae": 264, "##\u010a": 265, "##h": 266, "##\u0119": 267, "##\u011a": 268, "##\u00e7": 269, "##2": 270, "##\u00ac": 271, "##\u0139": 272, "##Z": 273, "##C": 274, "##-": 275, "##\u0124": 276, "##=": 277, "##f": 278, "##\u0132": 279, "##\u011c": 280, "##^": 281, "##H": 282, "##w": 283, "##\u00e2": 284, "##\u00f4": 285, "##\\": 286, "##\u011d": 287, "##O": 288, "##\u013d": 289, "##V": 290, "##\u0111": 291, "##?": 292, "##i": 293, "##\u00d3": 294, "##\u00d5": 295, "##\u00e8": 296, "##\u00fe": 297, "##7": 298, "##\u00a2": 299, "##\u00c3": 300, "##\u0100": 301, "##\u0122": 302, "##\"": 303, "##x": 304, "##_": 305, "##\u00cb": 306, "##\u0101": 307, "##\u00c2": 308, "##\u0123": 309, "##\u00d4": 310, "##\u0129": 311, "##>": 312, "##\u00e5": 313, "##%": 314, "##\u00fc": 315, "##\u00f7": 316, "##\u00d8": 317, "##\u00cc": 318, "##F": 319, "##4": 320, "##\u00b6": 321, "##\u00a9": 322, "##\u00a5": 323, "##\u0108": 324, "##c": 325, "##]": 326, "##)": 327, "##\u0127": 328, "##\u0114": 329, "##\u012e": 330, "##\u013e": 331, "##\u00ba": 332, "##\u00ce": 333, "##\u00d0": 334, "##(": 335, "##|": 336, "##\u00d6": 337, "##\u00ec": 338, "##\u00fa": 339, "##\u00aa": 340, "##\u00da": 341, "##\u010c": 342, "##.": 343, "##\u00b9": 344, "##\u00bd": 345, "##\u013f": 346, "##;": 347, "##\u00ed": 348, "##\u00b4": 349, "##b": 350, "##\u00a4": 351, "##\u00c0": 352, "##\u00cf": 353, "##G": 354, "##P": 355, "##\u00a6": 356, "##\u00ef": 357, "##\u0106": 358, "##\u012b": 359, "##\u0104": 360, "##R": 361, "##\u0103": 362, "##s": 363, "##3": 364, "##I": 365, "##\u00b1": 366, "##\u0130": 367, "##\u00a3": 368, "##\u0102": 369, "##0": 370, "##\u0110": 371, "##\u0142": 372, "##\u0125": 373, "##\u00f3": 374, "##\u00f5": 375, "##\u00fb": 376, "##\u0137": 377, "##D": 378, "##z": 379, "##\u010e": 380, "##\u0138": 381, "##\u00bf": 382, "##\u00d7": 383, "##k": 384, "##1": 385, "##\u00de": 386, "##\u00e6": 387, "##$": 388, "##A": 389, "##\u00f1": 390, "##\u012c": 391, "##\u00b3": 392, "##:": 393, "##\u00c1": 394, "##\u010f": 395, "##\u00a7": 396, "##\u00ff": 397, "##\u012a": 398, "##\u013b": 399, "##B": 400, "##\u00c5": 401, "##\u0121": 402, "##\u00e9": 403, "##\u0131": 404, "##\u013a": 405, "##\u00dc": 406, "##\u00b2": 407, "##6": 408, "##\u00b7": 409, "##\u00b8": 410, "##\u00ea": 411, "##\u00ca": 412, "##<": 413, "##U": 414, "##\u0120": 415, "##e": 416, "##5": 417, "##!": 418, "##\u00f6": 419, "##L": 420, "##X": 421, "##M": 422, "##\u00c8": 423, "##\u0115": 424, "##\u0116": 425, "##\u0136": 426, "##S": 427, "##l": 428, "##\u00bb": 429, "##\u00d2": 430, "##\u00f9": 431, "##\u0107": 432, "##&": 433, "##\u00e0": 434, "##@": 435, "##\u00fd": 436, "##\u00c4": 437, "##p": 438, "##\u00ee": 439, "##\u00df": 440, "##\u00f8": 441, "##t": 442, "##\u00b5": 443, "##\u00c9": 444, "##\u0112": 445, "##d": 446, "##\u010b": 447, "##\u011b": 448, "##\u0141": 449, "##8": 450, "##\u00e3": 451, "##\u0135": 452, "##\u00c6": 453, "##\u00a1": 454, "##\u0143": 455, "##n": 456, "##\u00bc": 457, "##j": 458, "##\u00cd": 459, "##\u0128": 460, "##r": 461, "##\u0118": 462, "##\u00d9": 463, "##\u0133": 464, "##\u011e": 465, "##\u011f": 466, "##\u0105": 467, "##\u00eb": 468, "##+": 469, "##\u00af": 470, "##\u0117": 471, "##/": 472, "##q": 473, "##\u00d1": 474, "##\u0126": 475, "##W": 476, "##[": 477, "##\u00e4": 478, "##\u00c7": 479, "##\u012d": 480, "##\u013c": 481, "##\u00b0": 482, "##o": 483, "##\u00dd": 484, "##u": 485, "##m": 486, "##\u0113": 487, "##g": 488, "###": 489, "##y": 490, "##v": 491, "##\u0140": 492, "##\u00be": 493, "##'": 494, "##a": 495, "##K": 496, "##T": 497, "##~": 498, "##`": 499, "##\u00db": 500, "##{": 501, "##\u00ab": 502, "##\u00e1": 503, "##N": 504, "##\u0109": 505, "##\u012f": 506, "##\u00f0": 507, "##\u0134": 508, "##}": 509, "##*": 510, "##J": 511, "##\u00f2": 512, "##,": 513, "<|unk|>": 514, "##ng": 515, "##\ufffd": 516, "##er": 517, "##nt": 518, "##en": 519, "##on": 520, "##le": 521, "##nd": 522, "##her": 523, "##ent": 524, "##ss": 525, "##gh": 526, "##se": 527, "##em": 528, "##ur": 529, "##he": 530, "##in": 531, "##es": 532, "##th": 533, "##ct": 534, "##al": 535, "##us": 536, "##ar": 537, "##ge": 538, "##at": 539, "##io": 540, "##ve": 541, "##ld": 542, "##ce": 543, "##ion": 544, "##or": 545, "##ple": 546, "##ch": 547, "##te": 548, "##ll": 549, "##me": 550, "##ul": 551, "##re": 552, "##og": 553, "##ti": 554, "##an": 555, "##ra": 556, "##lt": 557, "##rd": 558, "##el": 559, "##ht": 560, "##st": 561, "##ag": 562, "##ut": 563, "##pl": 564, "##ue": 565, "##ing": 566, "##de": 567, "##ow": 568, "##rg": 569, "##ect": 570, "##is": 571, "##et": 572, "##tr": 573, "##ay": 574, "##ma": 575, "##it": 576, "##il": 577, "##ri": 578, "##dy": 579, "##use": 580, "##bl": 581, "##ly": 582, "##and": 583, "##li": 584, "##ne": 585, "##ic": 586, "##tem": 587, "##ed": 588, "##ess": 589, "##as": 590, "##ou": 591, "##ec": 592, "##om": 593, "##uc": 594, "##ke": 595, "##ia": 596, "##ud": 597, "##sh": 598, "##na": 599}