codebyzeb commited on
Commit
53333c9
·
verified ·
1 Parent(s): d000429

Upload folder using huggingface_hub

Browse files
fw57M_Entropy_thresholdBX_600/stats.csv CHANGED
@@ -1,129 +1,404 @@
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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  num_moves,vocab_size,unique_segments,threshold
2
+ 0,260,1,5.133828295811327e-08
3
+ 1000,261,22,9.790553576749517e-07
4
+ 2000,261,25,1.4309060816231067e-06
5
+ 3000,261,27,1.8229197848995682e-06
6
+ 4000,262,30,2.1990540517435875e-06
7
+ 5000,262,34,2.5248320980608696e-06
8
+ 6000,262,37,2.8365827802190324e-06
9
+ 7000,262,39,3.127169520666939e-06
10
+ 8000,262,42,3.4406789382046554e-06
11
+ 9000,262,44,3.7212562347122002e-06
12
+ 10000,262,46,4.012302269984502e-06
13
+ 11000,262,47,4.296648512536194e-06
14
+ 12000,262,49,4.568334588839207e-06
15
+ 13000,263,54,4.853022801398765e-06
16
+ 14000,263,58,5.109339326736517e-06
17
+ 15000,263,65,5.373932253860403e-06
18
+ 16000,263,67,5.649672857543919e-06
19
+ 17000,263,69,5.914777375437552e-06
20
+ 18000,263,73,6.172143912408501e-06
21
+ 19000,264,76,6.424897492252057e-06
22
+ 20000,265,77,6.700956419081194e-06
23
+ 21000,265,81,6.9617381086573005e-06
24
+ 22000,265,84,7.22233698979835e-06
25
+ 23000,266,86,7.478172392438864e-06
26
+ 24000,266,92,7.740409273537807e-06
27
+ 25000,266,94,8.001956302905455e-06
28
+ 26000,266,98,8.264463758678176e-06
29
+ 27000,267,104,8.528708349331282e-06
30
+ 28000,267,107,8.773720765020698e-06
31
+ 29000,267,109,9.04225635167677e-06
32
+ 30000,268,113,9.290170055464841e-06
33
+ 31000,268,117,9.528370355837978e-06
34
+ 32000,269,118,9.79736796580255e-06
35
+ 33000,270,122,1.0070482858282048e-05
36
+ 34000,270,127,1.0339319487684406e-05
37
+ 35000,270,129,1.0614803613862023e-05
38
+ 36000,271,133,1.0890100384131074e-05
39
+ 37000,272,135,1.1162222108396236e-05
40
+ 38000,272,139,1.1431737220846117e-05
41
+ 39000,272,139,1.1706975783454254e-05
42
+ 40000,273,143,1.1987172001681756e-05
43
+ 41000,274,148,1.224808602273697e-05
44
+ 42000,274,150,1.2501597666414455e-05
45
+ 43000,274,152,1.2784775208274368e-05
46
+ 44000,274,154,1.307702677877387e-05
47
+ 45000,275,154,1.3359001059143338e-05
48
+ 46000,276,157,1.3647608284372836e-05
49
+ 47000,277,158,1.3921197023591958e-05
50
+ 48000,278,161,1.4208838365448173e-05
51
+ 49000,278,162,1.4507069863611832e-05
52
+ 50000,278,166,1.4814748283242807e-05
53
+ 51000,279,168,1.5173626707110088e-05
54
+ 52000,279,170,1.5574130884488113e-05
55
+ 53000,280,173,1.6095349565148354e-05
56
+ 54000,280,174,1.6789324945420958e-05
57
+ 55000,281,178,1.7530710465507582e-05
58
+ 56000,281,182,1.807898297556676e-05
59
+ 57000,281,186,1.855349910329096e-05
60
+ 58000,282,189,1.89148177014431e-05
61
+ 59000,286,192,1.9255410734331235e-05
62
+ 60000,286,196,1.9606726709753275e-05
63
+ 61000,286,198,1.993944897549227e-05
64
+ 62000,288,202,2.026474612648599e-05
65
+ 63000,288,204,2.057795245491434e-05
66
+ 64000,288,208,2.0897583453916013e-05
67
+ 65000,289,210,2.1221829229034483e-05
68
+ 66000,290,212,2.1535339328693226e-05
69
+ 67000,293,219,2.1876883693039417e-05
70
+ 68000,295,220,2.2192627511685714e-05
71
+ 69000,298,224,2.2512333089252934e-05
72
+ 70000,299,225,2.281865272379946e-05
73
+ 71000,299,228,2.3127340682549402e-05
74
+ 72000,299,231,2.3458222131012008e-05
75
+ 73000,300,237,2.3790689738234505e-05
76
+ 74000,303,238,2.412626963632647e-05
77
+ 75000,304,239,2.4468832634738646e-05
78
+ 76000,305,240,2.481048068148084e-05
79
+ 77000,306,242,2.5139239369309507e-05
80
+ 78000,306,246,2.5478828320046887e-05
81
+ 79000,306,249,2.5810599254327826e-05
82
+ 80000,307,252,2.6150766643695533e-05
83
+ 81000,308,255,2.6495927158975974e-05
84
+ 82000,309,256,2.6845029424293898e-05
85
+ 83000,309,259,2.7201735065318644e-05
86
+ 84000,309,263,2.755965215328615e-05
87
+ 85000,309,267,2.7887075702892616e-05
88
+ 86000,311,272,2.823129943863023e-05
89
+ 87000,311,274,2.858073821698781e-05
90
+ 88000,312,275,2.8935739464941435e-05
91
+ 89000,312,280,2.9296392312971875e-05
92
+ 90000,313,286,2.9659753636224195e-05
93
+ 91000,313,292,3.002668745466508e-05
94
+ 92000,316,295,3.0397197406273335e-05
95
+ 93000,316,299,3.074545384151861e-05
96
+ 94000,316,301,3.1101779313758016e-05
97
+ 95000,316,305,3.149575786665082e-05
98
+ 96000,316,307,3.189174094586633e-05
99
+ 97000,316,309,3.22468149533961e-05
100
+ 98000,318,314,3.26372537529096e-05
101
+ 99000,320,319,3.3024651202140376e-05
102
+ 100000,320,322,3.339877730468288e-05
103
+ 101000,321,330,3.377669054316357e-05
104
+ 102000,321,334,3.417441257624887e-05
105
+ 103000,321,339,3.456857302808203e-05
106
+ 104000,321,344,3.496912540867925e-05
107
+ 105000,321,349,3.5385990486247465e-05
108
+ 106000,322,354,3.575959999579936e-05
109
+ 107000,322,358,3.61450802301988e-05
110
+ 108000,323,359,3.653268504422158e-05
111
+ 109000,324,363,3.6942012229701504e-05
112
+ 110000,326,370,3.730935713974759e-05
113
+ 111000,327,373,3.769703835132532e-05
114
+ 112000,329,378,3.8120309909572825e-05
115
+ 113000,330,383,3.853967791656032e-05
116
+ 114000,330,386,3.8975511415628716e-05
117
+ 115000,333,393,3.93725567846559e-05
118
+ 116000,333,397,3.9807622670196e-05
119
+ 117000,334,402,4.022541907033883e-05
120
+ 118000,334,405,4.067840927746147e-05
121
+ 119000,338,408,4.113887916901149e-05
122
+ 120000,339,411,4.1620303818490356e-05
123
+ 121000,341,414,4.212183193885721e-05
124
+ 122000,341,418,4.26527694799006e-05
125
+ 123000,343,421,4.322654058341868e-05
126
+ 124000,343,422,4.3803440348710865e-05
127
+ 125000,343,426,4.446713501238264e-05
128
+ 126000,343,431,4.5173615944804624e-05
129
+ 127000,345,435,4.5849425077904016e-05
130
+ 128000,345,440,4.65281555079855e-05
131
+ 129000,346,447,4.7097088099690154e-05
132
+ 130000,346,452,4.766680285683833e-05
133
+ 131000,346,455,4.817744775209576e-05
134
+ 132000,346,458,4.870327393291518e-05
135
+ 133000,346,461,4.920174251310527e-05
136
+ 134000,347,466,4.968308348907158e-05
137
+ 135000,347,470,5.017643343308009e-05
138
+ 136000,348,475,5.0663868023548275e-05
139
+ 137000,349,479,5.1141963922418654e-05
140
+ 138000,350,485,5.164055619388819e-05
141
+ 139000,350,490,5.2116614824626595e-05
142
+ 140000,350,493,5.258953387965448e-05
143
+ 141000,352,497,5.307243554852903e-05
144
+ 142000,354,499,5.356439214665443e-05
145
+ 143000,355,506,5.403726390795782e-05
146
+ 144000,356,513,5.4523996368516237e-05
147
+ 145000,356,519,5.499910548678599e-05
148
+ 146000,355,527,5.549181150854565e-05
149
+ 147000,355,533,5.5992106354096904e-05
150
+ 148000,356,535,5.6516106269555166e-05
151
+ 149000,356,542,5.702984344679862e-05
152
+ 150000,357,545,5.753296136390418e-05
153
+ 151000,357,552,5.804073589388281e-05
154
+ 152000,357,558,5.855420749867335e-05
155
+ 153000,359,561,5.9088684793096036e-05
156
+ 154000,360,567,5.9630576288327575e-05
157
+ 155000,360,574,6.0167138144606724e-05
158
+ 156000,359,578,6.067429785616696e-05
159
+ 157000,359,583,6.120924081187695e-05
160
+ 158000,361,589,6.172269058879465e-05
161
+ 159000,363,595,6.227569247130305e-05
162
+ 160000,365,599,6.282198592089117e-05
163
+ 161000,366,603,6.337612285278738e-05
164
+ 162000,366,608,6.394451338564977e-05
165
+ 163000,367,610,6.452309025917202e-05
166
+ 164000,369,615,6.510177627205849e-05
167
+ 165000,371,618,6.569121615029871e-05
168
+ 166000,371,626,6.630591815337539e-05
169
+ 167000,373,638,6.693345494568348e-05
170
+ 168000,373,642,6.759059760952368e-05
171
+ 169000,374,649,6.822018622187898e-05
172
+ 170000,374,656,6.889564247103408e-05
173
+ 171000,376,660,6.960536848055199e-05
174
+ 172000,375,669,7.03365876688622e-05
175
+ 173000,378,674,7.111056038411334e-05
176
+ 174000,379,681,7.18764858902432e-05
177
+ 175000,379,688,7.268117769854143e-05
178
+ 176000,380,693,7.343306788243353e-05
179
+ 177000,381,699,7.421991904266179e-05
180
+ 178000,382,701,7.493997691199183e-05
181
+ 179000,382,711,7.568250293843448e-05
182
+ 180000,383,717,7.634618668816984e-05
183
+ 181000,385,725,7.700482092332095e-05
184
+ 182000,386,731,7.760989683447406e-05
185
+ 183000,386,735,7.826130604371428e-05
186
+ 184000,387,745,7.892258145147935e-05
187
+ 185000,388,750,7.959445065353066e-05
188
+ 186000,391,754,8.023567352211103e-05
189
+ 187000,392,758,8.084762521320954e-05
190
+ 188000,392,763,8.148838969646022e-05
191
+ 189000,393,774,8.213626279029995e-05
192
+ 190000,393,782,8.276363223558292e-05
193
+ 191000,393,788,8.341415377799422e-05
194
+ 192000,394,794,8.410123700741678e-05
195
+ 193000,395,797,8.473030175082386e-05
196
+ 194000,395,805,8.538847032468766e-05
197
+ 195000,396,810,8.607128984294832e-05
198
+ 196000,397,813,8.677331788931042e-05
199
+ 197000,400,816,8.74913384905085e-05
200
+ 198000,400,820,8.819071808829904e-05
201
+ 199000,401,823,8.887527656042948e-05
202
+ 200000,404,831,8.96106066647917e-05
203
+ 201000,404,837,9.039176802616566e-05
204
+ 202000,403,844,9.116170258494094e-05
205
+ 203000,405,850,9.191161370836198e-05
206
+ 204000,405,855,9.268507710658014e-05
207
+ 205000,406,863,9.348066669190302e-05
208
+ 206000,407,867,9.431746002519503e-05
209
+ 207000,408,873,9.513343684375286e-05
210
+ 208000,409,877,9.600699559086934e-05
211
+ 209000,410,883,9.687518468126655e-05
212
+ 210000,411,890,9.775336366146803e-05
213
+ 211000,411,898,9.860962745733559e-05
214
+ 212000,412,906,9.952823893399909e-05
215
+ 213000,414,909,0.00010041777568403631
216
+ 214000,414,916,0.00010130731971003115
217
+ 215000,415,921,0.0001021612697513774
218
+ 216000,417,924,0.00010298722190782428
219
+ 217000,418,930,0.0001038184855133295
220
+ 218000,420,935,0.00010466543608345091
221
+ 219000,420,940,0.00010548390855547041
222
+ 220000,421,942,0.0001063163872458972
223
+ 221000,421,947,0.0001070987491402775
224
+ 222000,422,949,0.00010796061542350799
225
+ 223000,422,961,0.00010877475142478943
226
+ 224000,422,966,0.00010960102372337133
227
+ 225000,422,972,0.00011046299187000841
228
+ 226000,422,979,0.00011130447092000395
229
+ 227000,422,989,0.00011216900747967884
230
+ 228000,422,996,0.00011303589417366311
231
+ 229000,423,999,0.00011391702719265595
232
+ 230000,425,1006,0.00011477310908958316
233
+ 231000,425,1013,0.00011569355410756543
234
+ 232000,427,1018,0.00011659049050649628
235
+ 233000,428,1023,0.00011754433216992766
236
+ 234000,428,1026,0.0001184323919005692
237
+ 235000,428,1033,0.00011939684918615967
238
+ 236000,428,1042,0.00012038474233122543
239
+ 237000,430,1051,0.0001214050134876743
240
+ 238000,431,1057,0.00012243652599863708
241
+ 239000,431,1065,0.0001234794472111389
242
+ 240000,432,1071,0.00012448015331756324
243
+ 241000,432,1078,0.00012551326653920114
244
+ 242000,432,1079,0.00012652068107854575
245
+ 243000,432,1083,0.00012746831635013223
246
+ 244000,432,1089,0.00012846790195908397
247
+ 245000,434,1096,0.00012941929162479937
248
+ 246000,433,1101,0.000130387008539401
249
+ 247000,434,1107,0.0001313605607720092
250
+ 248000,437,1111,0.00013233150821179152
251
+ 249000,437,1117,0.00013329619832802564
252
+ 250000,437,1123,0.00013422507618088275
253
+ 251000,439,1132,0.00013517335173673928
254
+ 252000,443,1139,0.00013617899094242603
255
+ 253000,443,1145,0.00013713783118873835
256
+ 254000,443,1149,0.00013816852879244834
257
+ 255000,443,1157,0.00013914502051193267
258
+ 256000,446,1167,0.00014017309877090156
259
+ 257000,448,1178,0.0001412533165421337
260
+ 258000,450,1191,0.00014228984946385026
261
+ 259000,453,1196,0.00014341094356495887
262
+ 260000,453,1204,0.00014451243623625487
263
+ 261000,453,1207,0.00014568472397513688
264
+ 262000,454,1212,0.00014690117677673697
265
+ 263000,454,1220,0.00014807340630795807
266
+ 264000,456,1224,0.0001492309384047985
267
+ 265000,456,1234,0.0001503805397078395
268
+ 266000,456,1240,0.00015156104927882552
269
+ 267000,458,1244,0.00015271393931470811
270
+ 268000,458,1256,0.00015389203326776624
271
+ 269000,461,1266,0.00015501159941777587
272
+ 270000,461,1278,0.00015614868607372046
273
+ 271000,463,1283,0.00015728520520497113
274
+ 272000,464,1291,0.0001584065321367234
275
+ 273000,466,1297,0.00015955821436364204
276
+ 274000,467,1300,0.00016068721015471965
277
+ 275000,468,1307,0.00016185276035685092
278
+ 276000,468,1316,0.00016305287135764956
279
+ 277000,468,1321,0.00016424903878942132
280
+ 278000,468,1330,0.00016550265718251467
281
+ 279000,468,1339,0.0001666881435085088
282
+ 280000,468,1349,0.0001679726701695472
283
+ 281000,470,1353,0.00016916971071623266
284
+ 282000,471,1361,0.00017038031364791095
285
+ 283000,473,1370,0.00017168864724226296
286
+ 284000,474,1374,0.0001728986098896712
287
+ 285000,476,1383,0.00017415231559425592
288
+ 286000,477,1387,0.0001754020049702376
289
+ 287000,477,1391,0.00017670051602181047
290
+ 288000,478,1401,0.00017809536075219512
291
+ 289000,480,1406,0.00017944462888408452
292
+ 290000,482,1413,0.00018079427536576986
293
+ 291000,482,1418,0.0001821514160837978
294
+ 292000,484,1428,0.00018344901036471128
295
+ 293000,484,1435,0.0001847625244408846
296
+ 294000,485,1446,0.00018616612942423671
297
+ 295000,485,1453,0.00018746851128526032
298
+ 296000,485,1459,0.00018876550893764943
299
+ 297000,486,1470,0.0001900622883113101
300
+ 298000,486,1479,0.0001915221946546808
301
+ 299000,489,1484,0.00019285913731437176
302
+ 300000,489,1490,0.0001942789094755426
303
+ 301000,491,1498,0.00019575172336772084
304
+ 302000,491,1506,0.00019722759316209704
305
+ 303000,491,1511,0.00019872430129908025
306
+ 304000,492,1520,0.0002001468965318054
307
+ 305000,496,1525,0.00020151579519733787
308
+ 306000,501,1535,0.00020292762201279402
309
+ 307000,501,1545,0.00020436220802366734
310
+ 308000,502,1550,0.00020579525153152645
311
+ 309000,503,1554,0.00020730339747387916
312
+ 310000,503,1559,0.00020878612122032791
313
+ 311000,505,1570,0.00021032213408034295
314
+ 312000,507,1581,0.0002117837138939649
315
+ 313000,509,1585,0.0002133245870936662
316
+ 314000,512,1591,0.00021483484306372702
317
+ 315000,513,1597,0.00021635045413859189
318
+ 316000,513,1604,0.00021790519531350583
319
+ 317000,513,1615,0.00021950664813630283
320
+ 318000,514,1622,0.00022118353808764368
321
+ 319000,515,1635,0.0002227935183327645
322
+ 320000,515,1641,0.00022435876599047333
323
+ 321000,517,1652,0.00022602200624532998
324
+ 322000,519,1657,0.00022774652461521327
325
+ 323000,521,1666,0.00022938594338484108
326
+ 324000,520,1675,0.00023099598183762282
327
+ 325000,522,1686,0.00023261010937858373
328
+ 326000,524,1693,0.000234224324231036
329
+ 327000,526,1697,0.0002358121855650097
330
+ 328000,526,1703,0.0002374451287323609
331
+ 329000,527,1716,0.00023911608150228858
332
+ 330000,529,1727,0.0002407849970040843
333
+ 331000,531,1744,0.00024251457944046706
334
+ 332000,532,1758,0.00024430608027614653
335
+ 333000,532,1772,0.00024606334045529366
336
+ 334000,530,1784,0.0002478437381796539
337
+ 335000,530,1794,0.00024971706443466246
338
+ 336000,531,1802,0.0002515531377866864
339
+ 337000,532,1811,0.00025328798801638186
340
+ 338000,535,1823,0.0002551207144279033
341
+ 339000,536,1832,0.000256925675785169
342
+ 340000,536,1848,0.0002587272902019322
343
+ 341000,539,1859,0.0002605176414363086
344
+ 342000,540,1869,0.00026237175916321576
345
+ 343000,544,1879,0.0002641679020598531
346
+ 344000,545,1889,0.000266063871094957
347
+ 345000,546,1905,0.0002680012257769704
348
+ 346000,548,1914,0.0002699239703360945
349
+ 347000,548,1920,0.00027196985320188105
350
+ 348000,548,1931,0.00027384835993871093
351
+ 349000,548,1940,0.00027571473037824035
352
+ 350000,549,1944,0.000277652929071337
353
+ 351000,551,1946,0.0002795763430185616
354
+ 352000,553,1957,0.0002814822073560208
355
+ 353000,552,1971,0.00028348760679364204
356
+ 354000,553,1982,0.0002854005724657327
357
+ 355000,554,1993,0.00028733894578181207
358
+ 356000,555,2003,0.00028936093440279365
359
+ 357000,554,2012,0.0002913514617830515
360
+ 358000,555,2019,0.00029355392325669527
361
+ 359000,558,2024,0.0002955961390398443
362
+ 360000,559,2032,0.00029755185823887587
363
+ 361000,560,2046,0.0002996465773321688
364
+ 362000,561,2056,0.00030167921795509756
365
+ 363000,560,2068,0.00030380854150280356
366
+ 364000,559,2077,0.00030584013438783586
367
+ 365000,563,2085,0.00030792420147918165
368
+ 366000,564,2093,0.00031017986475490034
369
+ 367000,565,2099,0.00031226917053572834
370
+ 368000,565,2110,0.0003144284710288048
371
+ 369000,565,2120,0.00031653043697588146
372
+ 370000,568,2132,0.0003187659604009241
373
+ 371000,572,2147,0.0003208818379789591
374
+ 372000,572,2154,0.0003231980372220278
375
+ 373000,572,2166,0.00032535591162741184
376
+ 374000,572,2176,0.0003276872157584876
377
+ 375000,574,2184,0.00032999683753587306
378
+ 376000,575,2191,0.0003322716220282018
379
+ 377000,576,2199,0.0003345462027937174
380
+ 378000,577,2213,0.000336807977873832
381
+ 379000,580,2217,0.00033918675035238266
382
+ 380000,581,2226,0.00034146811231039464
383
+ 381000,582,2233,0.00034380436409264803
384
+ 382000,582,2243,0.00034617926576174796
385
+ 383000,583,2252,0.0003485771594569087
386
+ 384000,583,2266,0.00035104225389659405
387
+ 385000,585,2271,0.0003534924180712551
388
+ 386000,587,2284,0.0003558952594175935
389
+ 387000,589,2300,0.0003583163779694587
390
+ 388000,589,2311,0.000360596866812557
391
+ 389000,590,2322,0.00036301667569205165
392
+ 390000,591,2335,0.00036544198519550264
393
+ 391000,590,2343,0.00036799354711547494
394
+ 392000,593,2353,0.0003705002600327134
395
+ 393000,593,2360,0.0003730201569851488
396
+ 394000,594,2366,0.0003755545476451516
397
+ 395000,595,2372,0.0003781096893362701
398
+ 396000,597,2384,0.00038085225969552994
399
+ 397000,598,2393,0.00038338208105415106
400
+ 398000,598,2410,0.00038609805051237345
401
+ 399000,599,2426,0.00038875776226632297
402
+ 400000,598,2435,0.0003915056004188955
403
+ 401000,599,2446,0.0003942163602914661
404
+ 402000,601,2455,0.0003967653610743582
fw57M_Entropy_thresholdBX_600/tokenizer.json CHANGED
@@ -22,7 +22,7 @@
22
  "special": true
23
  },
24
  {
25
- "id": 514,
26
  "content": "<|unk|>",
27
  "single_word": false,
28
  "lstrip": false,
@@ -65,604 +65,603 @@
65
  "vocab": {
66
  "<|padding|>": 0,
67
  "<|endoftext|>": 1,
68
- "!": 2,
69
- "\"": 3,
70
- "#": 4,
71
- "$": 5,
72
- "%": 6,
73
- "&": 7,
74
- "'": 8,
75
- "(": 9,
76
- ")": 10,
77
- "*": 11,
78
- "+": 12,
79
- ",": 13,
80
- "-": 14,
81
- ".": 15,
82
- "/": 16,
83
- "0": 17,
84
- "1": 18,
85
- "2": 19,
86
- "3": 20,
87
- "4": 21,
88
- "5": 22,
89
- "6": 23,
90
- "7": 24,
91
- "8": 25,
92
- "9": 26,
93
- ":": 27,
94
- ";": 28,
95
- "<": 29,
96
- "=": 30,
97
- ">": 31,
98
- "?": 32,
99
- "@": 33,
100
- "A": 34,
101
- "B": 35,
102
- "C": 36,
103
- "D": 37,
104
- "E": 38,
105
- "F": 39,
106
- "G": 40,
107
- "H": 41,
108
- "I": 42,
109
- "J": 43,
110
- "K": 44,
111
- "L": 45,
112
- "M": 46,
113
- "N": 47,
114
- "O": 48,
115
- "P": 49,
116
- "Q": 50,
117
- "R": 51,
118
- "S": 52,
119
- "T": 53,
120
- "U": 54,
121
- "V": 55,
122
- "W": 56,
123
- "X": 57,
124
- "Y": 58,
125
- "Z": 59,
126
- "[": 60,
127
- "\\": 61,
128
- "]": 62,
129
- "^": 63,
130
- "_": 64,
131
- "`": 65,
132
- "a": 66,
133
- "b": 67,
134
- "c": 68,
135
- "d": 69,
136
- "e": 70,
137
- "f": 71,
138
- "g": 72,
139
- "h": 73,
140
- "i": 74,
141
- "j": 75,
142
- "k": 76,
143
- "l": 77,
144
- "m": 78,
145
- "n": 79,
146
- "o": 80,
147
- "p": 81,
148
- "q": 82,
149
- "r": 83,
150
- "s": 84,
151
- "t": 85,
152
- "u": 86,
153
- "v": 87,
154
- "w": 88,
155
- "x": 89,
156
- "y": 90,
157
- "z": 91,
158
- "{": 92,
159
- "|": 93,
160
- "}": 94,
161
- "~": 95,
162
- "¡": 96,
163
- "¢": 97,
164
- "£": 98,
165
- "¤": 99,
166
- "¥": 100,
167
- "¦": 101,
168
- "§": 102,
169
- "¨": 103,
170
- "©": 104,
171
- "ª": 105,
172
- "«": 106,
173
- "¬": 107,
174
- "®": 108,
175
- "¯": 109,
176
- "°": 110,
177
- "±": 111,
178
- "²": 112,
179
- "³": 113,
180
- "´": 114,
181
- "µ": 115,
182
- "": 116,
183
- "·": 117,
184
- "¸": 118,
185
- "¹": 119,
186
- "º": 120,
187
- "»": 121,
188
- "¼": 122,
189
- "½": 123,
190
- "¾": 124,
191
- "¿": 125,
192
- "À": 126,
193
- "Á": 127,
194
- "Â": 128,
195
- "Ã": 129,
196
- "Ä": 130,
197
- "Å": 131,
198
- "Æ": 132,
199
- "Ç": 133,
200
- "È": 134,
201
- "É": 135,
202
- "Ê": 136,
203
- "Ë": 137,
204
- "Ì": 138,
205
- "Í": 139,
206
- "Î": 140,
207
- "Ï": 141,
208
- "Ð": 142,
209
- "Ñ": 143,
210
- "Ò": 144,
211
- "Ó": 145,
212
- "Ô": 146,
213
- "Õ": 147,
214
- "Ö": 148,
215
- "×": 149,
216
- "Ø": 150,
217
- "Ù": 151,
218
- "Ú": 152,
219
- "Û": 153,
220
- "Ü": 154,
221
- "Ý": 155,
222
- "Þ": 156,
223
- "ß": 157,
224
- "à": 158,
225
- "á": 159,
226
- "â": 160,
227
- "ã": 161,
228
- "ä": 162,
229
- "å": 163,
230
- "æ": 164,
231
- "ç": 165,
232
- "è": 166,
233
- "é": 167,
234
- "ê": 168,
235
- "ë": 169,
236
- "ì": 170,
237
- "í": 171,
238
- "î": 172,
239
- "ï": 173,
240
- "ð": 174,
241
- "ñ": 175,
242
- "ò": 176,
243
- "ó": 177,
244
- "ô": 178,
245
- "õ": 179,
246
- "ö": 180,
247
- "÷": 181,
248
- "ø": 182,
249
- "ù": 183,
250
- "ú": 184,
251
- "û": 185,
252
- "ü": 186,
253
- "ý": 187,
254
- "þ": 188,
255
- "ÿ": 189,
256
- "Ā": 190,
257
- "ā": 191,
258
- "Ă": 192,
259
- "ă": 193,
260
- "Ą": 194,
261
- "ą": 195,
262
- "Ć": 196,
263
- "ć": 197,
264
- "Ĉ": 198,
265
- "ĉ": 199,
266
- "Ċ": 200,
267
- "ċ": 201,
268
- "Č": 202,
269
- "č": 203,
270
- "Ď": 204,
271
- "ď": 205,
272
- "Đ": 206,
273
- "đ": 207,
274
- "Ē": 208,
275
- "ē": 209,
276
- "Ĕ": 210,
277
- "ĕ": 211,
278
- "Ė": 212,
279
- "ė": 213,
280
- "Ę": 214,
281
- "ę": 215,
282
- "Ě": 216,
283
- "ě": 217,
284
- "Ĝ": 218,
285
- "ĝ": 219,
286
- "Ğ": 220,
287
- "ğ": 221,
288
- "Ġ": 222,
289
- "ġ": 223,
290
- "Ģ": 224,
291
- "ģ": 225,
292
- "Ĥ": 226,
293
- "ĥ": 227,
294
- "Ħ": 228,
295
- "ħ": 229,
296
- "Ĩ": 230,
297
- "ĩ": 231,
298
- "Ī": 232,
299
- "ī": 233,
300
- "Ĭ": 234,
301
- "ĭ": 235,
302
- "Į": 236,
303
- "į": 237,
304
- "İ": 238,
305
- "ı": 239,
306
- "IJ": 240,
307
- "ij": 241,
308
- "Ĵ": 242,
309
- "ĵ": 243,
310
- "Ķ": 244,
311
- "ķ": 245,
312
- "ĸ": 246,
313
- "Ĺ": 247,
314
- "ĺ": 248,
315
- "Ļ": 249,
316
- "ļ": 250,
317
- "Ľ": 251,
318
- "ľ": 252,
319
- "Ŀ": 253,
320
- "ŀ": 254,
321
- "Ł": 255,
322
- "ł": 256,
323
- "Ń": 257,
324
- "##Ċ": 258,
325
- "##m": 259,
326
- "##¤": 260,
327
- "##Ă": 261,
328
- "##!": 262,
329
- "###": 263,
330
- "##.": 264,
331
- "##8": 265,
332
- "##E": 266,
333
- "##×": 267,
334
- "##ì": 268,
335
- "##7": 269,
336
- "##I": 270,
337
- "##Ë": 271,
338
- "##L": 272,
339
- "##{": 273,
340
- "##+": 274,
341
- "##Ú": 275,
342
- "##ë": 276,
343
- "##Å": 277,
344
- "##Ç": 278,
345
- "##q": 279,
346
- "##î": 280,
347
- "##IJ": 281,
348
- "##²": 282,
349
- "##Ĺ": 283,
350
- "##¡": 284,
351
- "##Ĩ": 285,
352
- "##W": 286,
353
- "##Ï": 287,
354
- "##Ö": 288,
355
- "##Õ": 289,
356
- "##â": 290,
357
- "##ù": 291,
358
- "##U": 292,
359
- "##ď": 293,
360
- "##c": 294,
361
- "##ú": 295,
362
- "##¥": 296,
363
- "##2": 297,
364
- "##X": 298,
365
- "##Ù": 299,
366
- "##p": 300,
367
- "##0": 301,
368
- "##Ć": 302,
369
- "##y": 303,
370
- "##ð": 304,
371
- "##Ĵ": 305,
372
- "##ł": 306,
373
- "##]": 307,
374
- "##_": 308,
375
- "##h": 309,
376
- "##b": 310,
377
- "##B": 311,
378
- "##Û": 312,
379
- "##ó": 313,
380
- "##ô": 314,
381
- "##Ħ": 315,
382
- "##ļ": 316,
383
- "##$": 317,
384
- "##5": 318,
385
- "##M": 319,
386
- "##À": 320,
387
- "##G": 321,
388
- "##Ě": 322,
389
- "##÷": 323,
390
- "##Đ": 324,
391
- "##C": 325,
392
- "##ç": 326,
393
- "##º": 327,
394
- "##ħ": 328,
395
- "##Ļ": 329,
396
- "##e": 330,
397
- "##[": 331,
398
- "##Ā": 332,
399
- "##@": 333,
400
- "##v": 334,
401
- "##a": 335,
402
- "##ĥ": 336,
403
- "##V": 337,
404
- "##d": 338,
405
- "##j": 339,
406
- "##İ": 340,
407
- "##Ł": 341,
408
- "##~": 342,
409
- "##ě": 343,
410
- "##^": 344,
411
- "##©": 345,
412
- "##6": 346,
413
- "##ą": 347,
414
- "##±": 348,
415
- "##Ī": 349,
416
- "##o": 350,
417
- "##Y": 351,
418
- "##Z": 352,
419
- "##ŀ": 353,
420
- "##į": 354,
421
- "##ñ": 355,
422
- "##ö": 356,
423
- "##Ó": 357,
424
- "##ø": 358,
425
- "##Ô": 359,
426
- "##ß": 360,
427
- "##ģ": 361,
428
- "##Ä": 362,
429
- "##Ý": 363,
430
- "##u": 364,
431
- "##Ê": 365,
432
- "##Ñ": 366,
433
- "##Ò": 367,
434
- "##T": 368,
435
- "##¸": 369,
436
- "##Ü": 370,
437
- "##»": 371,
438
- "##Ē": 372,
439
- "##*": 373,
440
- "##¬": 374,
441
- "##Ď": 375,
442
- "##ē": 376,
443
- "##ī": 377,
444
- "##&": 378,
445
- "##å": 379,
446
- "##ċ": 380,
447
- "##r": 381,
448
- "##Ĝ": 382,
449
- "##«": 383,
450
- "##i": 384,
451
- "##Ĭ": 385,
452
- "##\"": 386,
453
- "##t": 387,
454
- "##ò": 388,
455
- "##?": 389,
456
- "##Ð": 390,
457
- "##ĵ": 391,
458
- "##Ń": 392,
459
- "##°": 393,
460
- "##ĺ": 394,
461
- "##w": 395,
462
- "##ă": 396,
463
- "##È": 397,
464
- "##é": 398,
465
- "##ij": 399,
466
- "##¯": 400,
467
- "##K": 401,
468
- "##Ã": 402,
469
- "##Č": 403,
470
- "##Ġ": 404,
471
- "##,": 405,
472
- "##ı": 406,
473
- "##4": 407,
474
- "##k": 408,
475
- "##µ": 409,
476
- "##%": 410,
477
- "##:": 411,
478
- "##í": 412,
479
- "##N": 413,
480
- "##ĭ": 414,
481
- "##¨": 415,
482
- "##Ľ": 416,
483
- "##x": 417,
484
- "##Ø": 418,
485
- "##É": 419,
486
- "##z": 420,
487
- "##ÿ": 421,
488
- "##Ķ": 422,
489
- "##/": 423,
490
- "##à": 424,
491
- "##3": 425,
492
- "##¦": 426,
493
- "##æ": 427,
494
- "##Î": 428,
495
- "##è": 429,
496
- "##·": 430,
497
- "##S": 431,
498
- "##ľ": 432,
499
- "##Þ": 433,
500
- "##ć": 434,
501
- "##ĉ": 435,
502
- "##f": 436,
503
- "##O": 437,
504
- "##Á": 438,
505
- "##9": 439,
506
- "##Ę": 440,
507
- "##s": 441,
508
- "##ã": 442,
509
- "##>": 443,
510
- "##Q": 444,
511
- "##<": 445,
512
- "##R": 446,
513
- "##®": 447,
514
- "##ė": 448,
515
- "##ĝ": 449,
516
- "##}": 450,
517
- "##Ė": 451,
518
- "##Ĉ": 452,
519
- "##|": 453,
520
- "##ý": 454,
521
- "##l": 455,
522
- "##(": 456,
523
- "##ĕ": 457,
524
- "##¢": 458,
525
- "##=": 459,
526
- "##ĸ": 460,
527
- "##'": 461,
528
- "##ę": 462,
529
- "##¿": 463,
530
- "##H": 464,
531
- "##ġ": 465,
532
- "##Æ": 466,
533
- "##Ą": 467,
534
- "##ü": 468,
535
- "##¹": 469,
536
- "##Ģ": 470,
537
- "##þ": 471,
538
- "##£": 472,
539
- "##á": 473,
540
- "##J": 474,
541
- "##§": 475,
542
- "##ğ": 476,
543
- "##Ğ": 477,
544
- "##õ": 478,
545
- "##ª": 479,
546
- "##½": 480,
547
- "##Ì": 481,
548
- "##Í": 482,
549
- "##ä": 483,
550
- "##ĩ": 484,
551
- "##-": 485,
552
- "##;": 486,
553
- "##û": 487,
554
- "##´": 488,
555
- "##¶": 489,
556
- "##č": 490,
557
- "##1": 491,
558
- "##A": 492,
559
- "##P": 493,
560
- "##\\": 494,
561
- "##`": 495,
562
- "##n": 496,
563
- "##Ĕ": 497,
564
- "##Į": 498,
565
- "##)": 499,
566
- "##Ŀ": 500,
567
- "##đ": 501,
568
- "##¼": 502,
569
- "##g": 503,
570
- "##Â": 504,
571
- "##ķ": 505,
572
- "##³": 506,
573
- "##ê": 507,
574
- "##Ĥ": 508,
575
- "##ï": 509,
576
- "##D": 510,
577
- "##¾": 511,
578
- "##ā": 512,
579
- "##F": 513,
580
- "<|unk|>": 514,
581
- "##ng": 515,
582
- "##�": 516,
583
- "##er": 517,
584
- "##nt": 518,
585
- "##en": 519,
586
- "##on": 520,
587
- "##le": 521,
588
- "##nd": 522,
589
- "##her": 523,
590
- "##ent": 524,
591
- "##ss": 525,
592
- "##gh": 526,
593
- "##se": 527,
594
- "##em": 528,
595
- "##ur": 529,
596
- "##he": 530,
597
- "##in": 531,
598
- "##es": 532,
599
- "##th": 533,
600
- "##ct": 534,
601
- "##al": 535,
602
- "##us": 536,
603
- "##ar": 537,
604
- "##ge": 538,
605
- "##at": 539,
606
- "##io": 540,
607
- "##ve": 541,
608
- "##ld": 542,
609
- "##ce": 543,
610
- "##ion": 544,
611
- "##or": 545,
612
- "##ple": 546,
613
- "##ch": 547,
614
- "##te": 548,
615
- "##ll": 549,
616
- "##me": 550,
617
- "##ul": 551,
618
- "##re": 552,
619
- "##og": 553,
620
- "##ti": 554,
621
- "##an": 555,
622
- "##ra": 556,
623
- "##lt": 557,
624
- "##rd": 558,
625
- "##el": 559,
626
- "##ht": 560,
627
- "##st": 561,
628
- "##ag": 562,
629
- "##ut": 563,
630
- "##pl": 564,
631
- "##ue": 565,
632
- "##ing": 566,
633
- "##de": 567,
634
- "##ow": 568,
635
- "##rg": 569,
636
- "##ect": 570,
637
- "##is": 571,
638
- "##et": 572,
639
- "##tr": 573,
640
- "##ay": 574,
641
- "##ma": 575,
642
- "##it": 576,
643
- "##il": 577,
644
- "##ri": 578,
645
- "##dy": 579,
646
- "##use": 580,
647
- "##bl": 581,
648
- "##ly": 582,
649
- "##and": 583,
650
- "##li": 584,
651
- "##ne": 585,
652
- "##ic": 586,
653
- "##tem": 587,
654
- "##ed": 588,
655
- "##ess": 589,
656
- "##as": 590,
657
- "##ou": 591,
658
- "##ec": 592,
659
- "##om": 593,
660
- "##uc": 594,
661
- "##ke": 595,
662
- "##ia": 596,
663
- "##ud": 597,
664
- "##sh": 598,
665
- "##na": 599
666
  }
667
  }
668
  }
 
22
  "special": true
23
  },
24
  {
25
+ "id": 599,
26
  "content": "<|unk|>",
27
  "single_word": false,
28
  "lstrip": false,
 
65
  "vocab": {
66
  "<|padding|>": 0,
67
  "<|endoftext|>": 1,
68
+ "Ġ": 3,
69
+ "##ľ": 4,
70
+ "##Æ": 5,
71
+ "##ą": 6,
72
+ "##Ě": 7,
73
+ "##Ý": 8,
74
+ "##-": 9,
75
+ "##«": 10,
76
+ "##Õ": 11,
77
+ "##Ï": 12,
78
+ "##ú": 13,
79
+ "##é": 14,
80
+ "##ĵ": 15,
81
+ "##IJ": 16,
82
+ "##¥": 17,
83
+ "##ğ": 18,
84
+ "##õ": 19,
85
+ "##÷": 20,
86
+ "##;": 21,
87
+ "###": 22,
88
+ "##¡": 23,
89
+ "##ð": 24,
90
+ "##i": 25,
91
+ "##Ī": 26,
92
+ "##(": 27,
93
+ "##Û": 28,
94
+ "##´": 29,
95
+ "##Ę": 30,
96
+ "##į": 31,
97
+ "##¹": 32,
98
+ "##f": 33,
99
+ "##_": 34,
100
+ "##ö": 35,
101
+ "##k": 36,
102
+ "##ÿ": 37,
103
+ "##r": 38,
104
+ "##T": 39,
105
+ "##ā": 40,
106
+ "##ĥ": 41,
107
+ "##Ã": 42,
108
+ "##e": 43,
109
+ "##Ò": 44,
110
+ "##ï": 45,
111
+ "##£": 46,
112
+ "##I": 47,
113
+ "##¿": 48,
114
+ "##ñ": 49,
115
+ "##č": 50,
116
+ "##ĭ": 51,
117
+ "##Y": 52,
118
+ "##Ð": 53,
119
+ "##%": 54,
120
+ "##:": 55,
121
+ "##X": 56,
122
+ "##¾": 57,
123
+ "##ü": 58,
124
+ "##Ľ": 59,
125
+ "##V": 60,
126
+ "##§": 61,
127
+ "##Ď": 62,
128
+ "##[": 63,
129
+ "##C": 64,
130
+ "##W": 65,
131
+ "##â": 66,
132
+ "##ã": 67,
133
+ "##Ĝ": 68,
134
+ "##Ē": 69,
135
+ "##Č": 70,
136
+ "##Ģ": 71,
137
+ "##v": 72,
138
+ "##)": 73,
139
+ "##ç": 74,
140
+ "##ĺ": 75,
141
+ "##Þ": 76,
142
+ "##{": 77,
143
+ "##¶": 78,
144
+ "##ė": 79,
145
+ "##î": 80,
146
+ "##¸": 81,
147
+ "##²": 82,
148
+ "##À": 83,
149
+ "##ĉ": 84,
150
+ "##å": 85,
151
+ "##Ö": 86,
152
+ "##/": 87,
153
+ "##ß": 88,
154
+ "##Ļ": 89,
155
+ "##}": 90,
156
+ "##þ": 91,
157
+ "##\"": 92,
158
+ "##4": 93,
159
+ "##ê": 94,
160
+ "##Ĕ": 95,
161
+ "##ł": 96,
162
+ "##l": 97,
163
+ "##¢": 98,
164
+ "##'": 99,
165
+ "##1": 100,
166
+ "##Į": 101,
167
+ "##M": 102,
168
+ "##Z": 103,
169
+ "##y": 104,
170
+ "##¼": 105,
171
+ "##Ç": 106,
172
+ "##¯": 107,
173
+ "##p": 108,
174
+ "##Ì": 109,
175
+ "##*": 110,
176
+ "##Ô": 111,
177
+ "##0": 112,
178
+ "##ý": 113,
179
+ "##Ñ": 114,
180
+ "##Ü": 115,
181
+ "##ì": 116,
182
+ "##¬": 117,
183
+ "##İ": 118,
184
+ "##ä": 119,
185
+ "##Ó": 120,
186
+ "##í": 121,
187
+ "##E": 122,
188
+ "##×": 123,
189
+ "##Ĺ": 124,
190
+ "##9": 125,
191
+ "##Ĩ": 126,
192
+ "##m": 127,
193
+ "##û": 128,
194
+ "##P": 129,
195
+ "##`": 130,
196
+ "##3": 131,
197
+ "##ô": 132,
198
+ "##È": 133,
199
+ "##G": 134,
200
+ "##¨": 135,
201
+ "##$": 136,
202
+ "##J": 137,
203
+ "##u": 138,
204
+ "##~": 139,
205
+ "##Ĥ": 140,
206
+ "##Ħ": 141,
207
+ "##ĩ": 142,
208
+ "##6": 143,
209
+ "##>": 144,
210
+ "##Î": 145,
211
+ "##Ń": 146,
212
+ "##ó": 147,
213
+ "##&": 148,
214
+ "##.": 149,
215
+ "##¦": 150,
216
+ "##=": 151,
217
+ "##ª": 152,
218
+ "##ċ": 153,
219
+ "##æ": 154,
220
+ "##7": 155,
221
+ "##8": 156,
222
+ "##d": 157,
223
+ "##±": 158,
224
+ "##ı": 159,
225
+ "##è": 160,
226
+ "##Ł": 161,
227
+ "##Â": 162,
228
+ "##2": 163,
229
+ "##Ä": 164,
230
+ "##Ė": 165,
231
+ "##h": 166,
232
+ "##¤": 167,
233
+ "##R": 168,
234
+ "##Ŀ": 169,
235
+ "##x": 170,
236
+ "##?": 171,
237
+ "##ę": 172,
238
+ "##z": 173,
239
+ "##ŀ": 174,
240
+ "##]": 175,
241
+ "##,": 176,
242
+ "##+": 177,
243
+ "##|": 178,
244
+ "##ġ": 179,
245
+ "##Ċ": 180,
246
+ "##®": 181,
247
+ "##g": 182,
248
+ "##ă": 183,
249
+ "##³": 184,
250
+ "##ĸ": 185,
251
+ "##ģ": 186,
252
+ "##©": 187,
253
+ "##ù": 188,
254
+ "##N": 189,
255
+ "##o": 190,
256
+ "##t": 191,
257
+ "##U": 192,
258
+ "##Đ": 193,
259
+ "##Ā": 194,
260
+ "##º": 195,
261
+ "##ķ": 196,
262
+ "##b": 197,
263
+ "##B": 198,
264
+ "##j": 199,
265
+ "##Ù": 200,
266
+ "##q": 201,
267
+ "##ò": 202,
268
+ "##Ă": 203,
269
+ "##ij": 204,
270
+ "##ø": 205,
271
+ "##Ú": 206,
272
+ "##ĝ": 207,
273
+ "##Ğ": 208,
274
+ "##S": 209,
275
+ "##H": 210,
276
+ "##Q": 211,
277
+ "##s": 212,
278
+ "##ď": 213,
279
+ "##Ķ": 214,
280
+ "##½": 215,
281
+ "##5": 216,
282
+ "##L": 217,
283
+ "##ĕ": 218,
284
+ "##@": 219,
285
+ "##!": 220,
286
+ "##ć": 221,
287
+ "##á": 222,
288
+ "##\\": 223,
289
+ "##Ĵ": 224,
290
+ "##ļ": 225,
291
+ "##Á": 226,
292
+ "##^": 227,
293
+ "##»": 228,
294
+ "##É": 229,
295
+ "##Ø": 230,
296
+ "##Ĉ": 231,
297
+ "##F": 232,
298
+ "##Ë": 233,
299
+ "##ě": 234,
300
+ "##ī": 235,
301
+ "##n": 236,
302
+ "##°": 237,
303
+ "##<": 238,
304
+ "##à": 239,
305
+ "##ē": 240,
306
+ "##Ġ": 241,
307
+ "##Ĭ": 242,
308
+ "##O": 243,
309
+ "##D": 244,
310
+ "##Å": 245,
311
+ "##ħ": 246,
312
+ "##c": 247,
313
+ "##Í": 248,
314
+ "##A": 249,
315
+ "##a": 250,
316
+ "##K": 251,
317
+ "##Ê": 252,
318
+ "##Ć": 253,
319
+ "##Ą": 254,
320
+ "##ë": 255,
321
+ "##µ": 256,
322
+ "##w": 257,
323
+ "##·": 258,
324
+ "##đ": 259,
325
+ "##ng": 260,
326
+ "##er": 261,
327
+ "##�": 262,
328
+ "##ent": 263,
329
+ "##on": 264,
330
+ "##nt": 265,
331
+ "##en": 266,
332
+ "##her": 267,
333
+ "##al": 268,
334
+ "##ct": 269,
335
+ "##nd": 270,
336
+ "##ion": 271,
337
+ "##in": 272,
338
+ "##es": 273,
339
+ "##th": 274,
340
+ "##at": 275,
341
+ "##le": 276,
342
+ "##gh": 277,
343
+ "##or": 278,
344
+ "##ss": 279,
345
+ "##ar": 280,
346
+ "##ld": 281,
347
+ "##ur": 282,
348
+ "##ch": 283,
349
+ "##ou": 284,
350
+ "##re": 285,
351
+ "##ti": 286,
352
+ "##us": 287,
353
+ "##st": 288,
354
+ "##se": 289,
355
+ "##ge": 290,
356
+ "##ht": 291,
357
+ "## ": 292,
358
+ "##ut": 293,
359
+ "##ing": 294,
360
+ "##ple": 295,
361
+ "##me": 296,
362
+ "##ul": 297,
363
+ "##tion": 298,
364
+ "##om": 299,
365
+ "##an": 300,
366
+ "##ic": 301,
367
+ "##ce": 302,
368
+ "##em": 303,
369
+ "##ra": 304,
370
+ "##ess": 305,
371
+ "##og": 306,
372
+ "##it": 307,
373
+ "##el": 308,
374
+ "##rt": 309,
375
+ "##uc": 310,
376
+ "##ve": 311,
377
+ "##ne": 312,
378
+ "##ue": 313,
379
+ "##te": 314,
380
+ "##ay": 315,
381
+ "##lt": 316,
382
+ "##ow": 317,
383
+ "##il": 318,
384
+ "##rd": 319,
385
+ "##ment": 320,
386
+ "##bl": 321,
387
+ "##ect": 322,
388
+ "##ma": 323,
389
+ "##ed": 324,
390
+ "##de": 325,
391
+ "##et": 326,
392
+ "##is": 327,
393
+ "##ll": 328,
394
+ "##ver": 329,
395
+ "##ri": 330,
396
+ "##tem": 331,
397
+ "##ud": 332,
398
+ "##ase": 333,
399
+ "##use": 334,
400
+ "##io": 335,
401
+ "##ad": 336,
402
+ "##rg": 337,
403
+ "##nc": 338,
404
+ "##rch": 339,
405
+ "##li": 340,
406
+ "##ip": 341,
407
+ "##ly": 342,
408
+ "##id": 343,
409
+ "##la": 344,
410
+ "##ugh": 345,
411
+ "##nce": 346,
412
+ "##rn": 347,
413
+ "##ter": 348,
414
+ "##rm": 349,
415
+ "##ia": 350,
416
+ "##and": 351,
417
+ "##ear": 352,
418
+ "##as": 353,
419
+ "##ag": 354,
420
+ "##ate": 355,
421
+ "##tr": 356,
422
+ "##he": 357,
423
+ "##od": 358,
424
+ "##ni": 359,
425
+ "##ty": 360,
426
+ "##ght": 361,
427
+ "##und": 362,
428
+ "##ta": 363,
429
+ "##lop": 364,
430
+ "##ore": 365,
431
+ "##si": 366,
432
+ "##gn": 367,
433
+ "##iv": 368,
434
+ "##sh": 369,
435
+ "##ol": 370,
436
+ "##lo": 371,
437
+ "##tor": 372,
438
+ "##ber": 373,
439
+ "##pl": 374,
440
+ "##un": 375,
441
+ "##ph": 376,
442
+ "##rk": 377,
443
+ "##een": 378,
444
+ "##ry": 379,
445
+ "##ard": 380,
446
+ "##out": 381,
447
+ "##rat": 382,
448
+ "##oy": 383,
449
+ "##ro": 384,
450
+ "##ith": 385,
451
+ "##lit": 386,
452
+ "##��": 387,
453
+ "##ther": 388,
454
+ "##ib": 389,
455
+ "##ure": 390,
456
+ "##lf": 391,
457
+ "##ck": 392,
458
+ "##mat": 393,
459
+ "##ish": 394,
460
+ "##ial": 395,
461
+ "##rc": 396,
462
+ "##ec": 397,
463
+ "##ca": 398,
464
+ "##ork": 399,
465
+ "##tu": 400,
466
+ "##est": 401,
467
+ "##mal": 402,
468
+ "##os": 403,
469
+ "##den": 404,
470
+ "##ee": 405,
471
+ "##dy": 406,
472
+ "##age": 407,
473
+ "##stem": 408,
474
+ "##ation": 409,
475
+ "##ke": 410,
476
+ "##am": 411,
477
+ "##na": 412,
478
+ "##to": 413,
479
+ "##ua": 414,
480
+ "##ain": 415,
481
+ "##pt": 416,
482
+ "##lem": 417,
483
+ "##ui": 418,
484
+ "##ous": 419,
485
+ "##are": 420,
486
+ "##ult": 421,
487
+ "##di": 422,
488
+ "##ween": 423,
489
+ "##we": 424,
490
+ "##iat": 425,
491
+ "##ding": 426,
492
+ "##pa": 427,
493
+ "##arch": 428,
494
+ "##ough": 429,
495
+ "##tur": 430,
496
+ "##ine": 431,
497
+ "##lar": 432,
498
+ "##uen": 433,
499
+ "##ional": 434,
500
+ "##lly": 435,
501
+ "##mple": 436,
502
+ "##men": 437,
503
+ "##ltur": 438,
504
+ "##sue": 439,
505
+ "##ays": 440,
506
+ "##op": 441,
507
+ "##ble": 442,
508
+ "##ant": 443,
509
+ "##um": 444,
510
+ "##wer": 445,
511
+ "##ci": 446,
512
+ "##rce": 447,
513
+ "##ood": 448,
514
+ "##ether": 449,
515
+ "##mber": 450,
516
+ "##tio": 451,
517
+ "##log": 452,
518
+ "##ga": 453,
519
+ "##cer": 454,
520
+ "##br": 455,
521
+ "##rv": 456,
522
+ "##sk": 457,
523
+ "##elf": 458,
524
+ "##ap": 459,
525
+ "##mp": 460,
526
+ "##ac": 461,
527
+ "##fe": 462,
528
+ "##ot": 463,
529
+ "##ity": 464,
530
+ "##sion": 465,
531
+ "##ati": 466,
532
+ "##tp": 467,
533
+ "##cl": 468,
534
+ "##ir": 469,
535
+ "##mi": 470,
536
+ "##ness": 471,
537
+ "##oo": 472,
538
+ "##has": 473,
539
+ "##mb": 474,
540
+ "##vi": 475,
541
+ "##cat": 476,
542
+ "##nk": 477,
543
+ "##ea": 478,
544
+ "##up": 479,
545
+ "##ey": 480,
546
+ "##end": 481,
547
+ "##rica": 482,
548
+ "##ally": 483,
549
+ "##ho": 484,
550
+ "##ack": 485,
551
+ "##tal": 486,
552
+ "##tic": 487,
553
+ "##but": 488,
554
+ "##ral": 489,
555
+ "##lat": 490,
556
+ "##ive": 491,
557
+ "##ere": 492,
558
+ "##ady": 493,
559
+ "##vel": 494,
560
+ "##ek": 495,
561
+ "##ond": 496,
562
+ "##be": 497,
563
+ "##ace": 498,
564
+ "##ria": 499,
565
+ "##rs": 500,
566
+ "##nat": 501,
567
+ "##tan": 502,
568
+ "##tra": 503,
569
+ "##ov": 504,
570
+ "##der": 505,
571
+ "##era": 506,
572
+ "##cult": 507,
573
+ "##tant": 508,
574
+ "##ram": 509,
575
+ "##fi": 510,
576
+ "##rse": 511,
577
+ "##ug": 512,
578
+ "##ition": 513,
579
+ "##ort": 514,
580
+ "##ha": 515,
581
+ "##no": 516,
582
+ "##ie": 517,
583
+ "##oss": 518,
584
+ "##ciat": 519,
585
+ "##rder": 520,
586
+ "##ark": 521,
587
+ "##mati": 522,
588
+ "##eo": 523,
589
+ "##iro": 524,
590
+ "##enc": 525,
591
+ "##ted": 526,
592
+ "##ime": 527,
593
+ "##ell": 528,
594
+ "##ual": 529,
595
+ "##tom": 530,
596
+ "##avio": 531,
597
+ "##wn": 532,
598
+ "##red": 533,
599
+ "##nu": 534,
600
+ "##fic": 535,
601
+ "##hool": 536,
602
+ "##ab": 537,
603
+ "##gl": 538,
604
+ "##ep": 539,
605
+ "##mph": 540,
606
+ "##unt": 541,
607
+ "##ig": 542,
608
+ "##ide": 543,
609
+ "##nal": 544,
610
+ "##pe": 545,
611
+ "##va": 546,
612
+ "##eas": 547,
613
+ "##ger": 548,
614
+ "##gu": 549,
615
+ "##eri": 550,
616
+ "##cti": 551,
617
+ "##nos": 552,
618
+ "##ause": 553,
619
+ "##nti": 554,
620
+ "##cle": 555,
621
+ "##av": 556,
622
+ "##hin": 557,
623
+ "##ps": 558,
624
+ "##eady": 559,
625
+ "##dent": 560,
626
+ "##ite": 561,
627
+ "##ture": 562,
628
+ "##ool": 563,
629
+ "##ka": 564,
630
+ "##dia": 565,
631
+ "##cul": 566,
632
+ "##oom": 567,
633
+ "##all": 568,
634
+ "##po": 569,
635
+ "##rld": 570,
636
+ "##act": 571,
637
+ "##str": 572,
638
+ "##ys": 573,
639
+ "##pen": 574,
640
+ "##ost": 575,
641
+ "##ok": 576,
642
+ "##man": 577,
643
+ "##yle": 578,
644
+ "##ale": 579,
645
+ "##ill": 580,
646
+ "##ultur": 581,
647
+ "##int": 582,
648
+ "##ula": 583,
649
+ "##eight": 584,
650
+ "##qu": 585,
651
+ "##rag": 586,
652
+ "##let": 587,
653
+ "##im": 588,
654
+ "##ns": 589,
655
+ "##min": 590,
656
+ "##anc": 591,
657
+ "##bit": 592,
658
+ "##ien": 593,
659
+ "##per": 594,
660
+ "##gra": 595,
661
+ "##ew": 596,
662
+ "##ev": 597,
663
+ "##trat": 598,
664
+ "##hing": 599
 
665
  }
666
  }
667
  }
fw57M_Entropy_thresholdBX_600/tokenizer_config.json CHANGED
@@ -17,7 +17,7 @@
17
  "single_word": false,
18
  "special": true
19
  },
20
- "514": {
21
  "content": "<|unk|>",
22
  "lstrip": false,
23
  "normalized": false,
 
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "599": {
21
  "content": "<|unk|>",
22
  "lstrip": false,
23
  "normalized": false,
fw57M_Entropy_thresholdBX_600/vocab.json CHANGED
@@ -1 +1 @@
1
- {"\u010a": 200, "m": 78, "\u00a4": 99, "\u0102": 192, "!": 2, "#": 4, ".": 15, "8": 25, "E": 38, "\u00d7": 149, "\u00ec": 170, "7": 24, "I": 42, "\u00cb": 137, "L": 45, "{": 92, "+": 12, "\u00da": 152, "<|endoftext|>": 1, "\u00eb": 169, "\u00c5": 131, "\u00c7": 133, "q": 82, "\u00ee": 172, "\u0132": 240, "\u00b2": 112, "\u0139": 247, "\u00a1": 96, "\u0128": 230, "W": 56, "\u00cf": 141, "\u00d6": 148, "\u00d5": 147, "\u00e2": 160, "\u00f9": 183, "U": 54, "\u010f": 205, "c": 68, "\u00fa": 184, "\u00a5": 100, "2": 19, "X": 57, "\u00d9": 151, "p": 81, "0": 17, "\u0106": 196, "y": 90, "\u00f0": 174, "\u0134": 242, "\u0142": 256, "]": 62, "_": 64, "h": 73, "b": 67, "B": 35, "\u00db": 153, "\u00f3": 177, "\u00f4": 178, "\u0126": 228, "\u013c": 250, "$": 5, "5": 22, "M": 46, "\u00c0": 126, "<|padding|>": 0, "G": 40, "\u011a": 216, "\u00f7": 181, "\u0110": 206, "C": 36, "\u00e7": 165, "\u00ba": 120, "\u0127": 229, "\u013b": 249, "e": 70, "[": 60, "\u0100": 190, "@": 33, "v": 87, "a": 66, "\u0125": 227, "V": 55, "d": 69, "j": 75, "\u0130": 238, "\u0141": 255, "~": 95, "\u011b": 217, "^": 63, "\u00a9": 104, "6": 23, "\u0105": 195, "\u00b1": 111, "\u012a": 232, "o": 80, "Y": 58, "Z": 59, "\u0140": 254, "\u012f": 237, "\u00f1": 175, "\u00f6": 180, "\u00d3": 145, "\u00f8": 182, "\u00d4": 146, "\u00df": 157, "\u0123": 225, "\u00c4": 130, "\u00dd": 155, "u": 86, "\u00ca": 136, "\u00d1": 143, "\u00d2": 144, "T": 53, "\u00b8": 118, "\u00dc": 154, "\u00bb": 121, "\u0112": 208, "*": 11, "\u00ac": 107, "\u010e": 204, "\u0113": 209, "\u012b": 233, "&": 7, "\u00e5": 163, "\u010b": 201, "r": 83, "\u011c": 218, "\u00ab": 106, "i": 74, "\u012c": 234, "\"": 3, "t": 85, "\u00f2": 176, "?": 32, "\u00d0": 142, "\u0135": 243, "\u0143": 257, "\u00b0": 110, "\u013a": 248, "w": 88, "\u0103": 193, "\u00c8": 134, "\u00e9": 167, "\u0133": 241, "\u00af": 109, "K": 44, "\u00c3": 129, "\u010c": 202, "\u0120": 222, ",": 13, "\u0131": 239, "4": 21, "k": 76, "\u00b5": 115, "%": 6, ":": 27, "\u00ed": 171, "N": 47, "\u012d": 235, "\u00a8": 103, "\u013d": 251, "x": 89, "\u00d8": 150, "\u00c9": 135, "z": 91, "\u00ff": 189, "\u0136": 244, "/": 16, "\u00e0": 158, "3": 20, "\u00a6": 101, "\u00e6": 164, "\u00ce": 140, "\u00e8": 166, "\u00b7": 117, "S": 52, "\u013e": 252, "\u00de": 156, "\u0107": 197, "\u0109": 199, "f": 71, "O": 48, "\u00c1": 127, "9": 26, "\u0118": 214, "s": 84, "\u00e3": 161, ">": 31, "Q": 50, "<": 29, "R": 51, "\u00ae": 108, "\u0117": 213, "\u011d": 219, "}": 94, "\u0116": 212, "\u0108": 198, "|": 93, "\u00fd": 187, "l": 77, "(": 9, "\u0115": 211, "\u00a2": 97, "=": 30, "\u0138": 246, "'": 8, "\u0119": 215, "\u00bf": 125, "H": 41, "\u0121": 223, "\u00c6": 132, "\u0104": 194, "\u00fc": 186, "\u00b9": 119, "\u0122": 224, "\u00fe": 188, "\u00a3": 98, "\u00e1": 159, "J": 43, "\u00a7": 102, "\u011f": 221, "\u011e": 220, "\u00f5": 179, "\u00aa": 105, "\u00bd": 123, "\u00cc": 138, "\u00cd": 139, "\u00e4": 162, "\u0129": 231, "-": 14, ";": 28, "\u00fb": 185, "\u00b4": 114, "\u00b6": 116, "\u010d": 203, "1": 18, "A": 34, "P": 49, "\\": 61, "`": 65, "n": 79, "\u0114": 210, "\u012e": 236, ")": 10, "\u013f": 253, "\u0111": 207, "\u00bc": 122, "g": 72, "\u00c2": 128, "\u0137": 245, "\u00b3": 113, "\u00ea": 168, "\u0124": 226, "\u00ef": 173, "D": 37, "\u00be": 124, "\u0101": 191, "F": 39, "##\u010a": 258, "##m": 259, "##\u00a4": 260, "##\u0102": 261, "##!": 262, "###": 263, "##.": 264, "##8": 265, "##E": 266, "##\u00d7": 267, "##\u00ec": 268, "##7": 269, "##I": 270, "##\u00cb": 271, "##L": 272, "##{": 273, "##+": 274, "##\u00da": 275, "##\u00eb": 276, "##\u00c5": 277, "##\u00c7": 278, "##q": 279, "##\u00ee": 280, "##\u0132": 281, "##\u00b2": 282, "##\u0139": 283, "##\u00a1": 284, "##\u0128": 285, "##W": 286, "##\u00cf": 287, "##\u00d6": 288, "##\u00d5": 289, "##\u00e2": 290, "##\u00f9": 291, "##U": 292, "##\u010f": 293, "##c": 294, "##\u00fa": 295, "##\u00a5": 296, "##2": 297, "##X": 298, "##\u00d9": 299, "##p": 300, "##0": 301, "##\u0106": 302, "##y": 303, "##\u00f0": 304, "##\u0134": 305, "##\u0142": 306, "##]": 307, "##_": 308, "##h": 309, "##b": 310, "##B": 311, "##\u00db": 312, "##\u00f3": 313, "##\u00f4": 314, "##\u0126": 315, "##\u013c": 316, "##$": 317, "##5": 318, "##M": 319, "##\u00c0": 320, "##G": 321, "##\u011a": 322, "##\u00f7": 323, "##\u0110": 324, "##C": 325, "##\u00e7": 326, "##\u00ba": 327, "##\u0127": 328, "##\u013b": 329, "##e": 330, "##[": 331, "##\u0100": 332, "##@": 333, "##v": 334, "##a": 335, "##\u0125": 336, "##V": 337, "##d": 338, "##j": 339, "##\u0130": 340, "##\u0141": 341, "##~": 342, "##\u011b": 343, "##^": 344, "##\u00a9": 345, "##6": 346, "##\u0105": 347, "##\u00b1": 348, "##\u012a": 349, "##o": 350, "##Y": 351, "##Z": 352, "##\u0140": 353, "##\u012f": 354, "##\u00f1": 355, "##\u00f6": 356, "##\u00d3": 357, "##\u00f8": 358, "##\u00d4": 359, "##\u00df": 360, "##\u0123": 361, "##\u00c4": 362, "##\u00dd": 363, "##u": 364, "##\u00ca": 365, "##\u00d1": 366, "##\u00d2": 367, "##T": 368, "##\u00b8": 369, "##\u00dc": 370, "##\u00bb": 371, "##\u0112": 372, "##*": 373, "##\u00ac": 374, "##\u010e": 375, "##\u0113": 376, "##\u012b": 377, "##&": 378, "##\u00e5": 379, "##\u010b": 380, "##r": 381, "##\u011c": 382, "##\u00ab": 383, "##i": 384, "##\u012c": 385, "##\"": 386, "##t": 387, "##\u00f2": 388, "##?": 389, "##\u00d0": 390, "##\u0135": 391, "##\u0143": 392, "##\u00b0": 393, "##\u013a": 394, "##w": 395, "##\u0103": 396, "##\u00c8": 397, "##\u00e9": 398, "##\u0133": 399, "##\u00af": 400, "##K": 401, "##\u00c3": 402, "##\u010c": 403, "##\u0120": 404, "##,": 405, "##\u0131": 406, "##4": 407, "##k": 408, "##\u00b5": 409, "##%": 410, "##:": 411, "##\u00ed": 412, "##N": 413, "##\u012d": 414, "##\u00a8": 415, "##\u013d": 416, "##x": 417, "##\u00d8": 418, "##\u00c9": 419, "##z": 420, "##\u00ff": 421, "##\u0136": 422, "##/": 423, "##\u00e0": 424, "##3": 425, "##\u00a6": 426, "##\u00e6": 427, "##\u00ce": 428, "##\u00e8": 429, "##\u00b7": 430, "##S": 431, "##\u013e": 432, "##\u00de": 433, "##\u0107": 434, "##\u0109": 435, "##f": 436, "##O": 437, "##\u00c1": 438, "##9": 439, "##\u0118": 440, "##s": 441, "##\u00e3": 442, "##>": 443, "##Q": 444, "##<": 445, "##R": 446, "##\u00ae": 447, "##\u0117": 448, "##\u011d": 449, "##}": 450, "##\u0116": 451, "##\u0108": 452, "##|": 453, "##\u00fd": 454, "##l": 455, "##(": 456, "##\u0115": 457, "##\u00a2": 458, "##=": 459, "##\u0138": 460, "##'": 461, "##\u0119": 462, "##\u00bf": 463, "##H": 464, "##\u0121": 465, "##\u00c6": 466, "##\u0104": 467, "##\u00fc": 468, "##\u00b9": 469, "##\u0122": 470, "##\u00fe": 471, "##\u00a3": 472, "##\u00e1": 473, "##J": 474, "##\u00a7": 475, "##\u011f": 476, "##\u011e": 477, "##\u00f5": 478, "##\u00aa": 479, "##\u00bd": 480, "##\u00cc": 481, "##\u00cd": 482, "##\u00e4": 483, "##\u0129": 484, "##-": 485, "##;": 486, "##\u00fb": 487, "##\u00b4": 488, "##\u00b6": 489, "##\u010d": 490, "##1": 491, "##A": 492, "##P": 493, "##\\": 494, "##`": 495, "##n": 496, "##\u0114": 497, "##\u012e": 498, "##)": 499, "##\u013f": 500, "##\u0111": 501, "##\u00bc": 502, "##g": 503, "##\u00c2": 504, "##\u0137": 505, "##\u00b3": 506, "##\u00ea": 507, "##\u0124": 508, "##\u00ef": 509, "##D": 510, "##\u00be": 511, "##\u0101": 512, "##F": 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}
 
1
+ {"<|padding|>": 0, "<|endoftext|>": 1, "<|unk|>": 260, "\u0120": 3, "##\u013e": 4, "##\u00c6": 5, "##\u0105": 6, "##\u011a": 7, "##\u00dd": 8, "##-": 9, "##\u00ab": 10, "##\u00d5": 11, "##\u00cf": 12, "##\u00fa": 13, "##\u00e9": 14, "##\u0135": 15, "##\u0132": 16, "##\u00a5": 17, "##\u011f": 18, "##\u00f5": 19, "##\u00f7": 20, "##;": 21, "###": 22, "##\u00a1": 23, "##\u00f0": 24, "##i": 25, "##\u012a": 26, "##(": 27, "##\u00db": 28, "##\u00b4": 29, "##\u0118": 30, "##\u012f": 31, "##\u00b9": 32, "##f": 33, "##_": 34, "##\u00f6": 35, "##k": 36, "##\u00ff": 37, "##r": 38, "##T": 39, "##\u0101": 40, "##\u0125": 41, "##\u00c3": 42, "##e": 43, "##\u00d2": 44, "##\u00ef": 45, "##\u00a3": 46, "##I": 47, "##\u00bf": 48, "##\u00f1": 49, "##\u010d": 50, "##\u012d": 51, "##Y": 52, "##\u00d0": 53, "##%": 54, "##:": 55, "##X": 56, "##\u00be": 57, "##\u00fc": 58, "##\u013d": 59, "##V": 60, "##\u00a7": 61, "##\u010e": 62, "##[": 63, "##C": 64, "##W": 65, "##\u00e2": 66, "##\u00e3": 67, "##\u011c": 68, "##\u0112": 69, "##\u010c": 70, "##\u0122": 71, "##v": 72, "##)": 73, "##\u00e7": 74, "##\u013a": 75, "##\u00de": 76, "##{": 77, "##\u00b6": 78, "##\u0117": 79, "##\u00ee": 80, "##\u00b8": 81, "##\u00b2": 82, "##\u00c0": 83, "##\u0109": 84, "##\u00e5": 85, "##\u00d6": 86, "##/": 87, "##\u00df": 88, "##\u013b": 89, "##}": 90, "##\u00fe": 91, "##\"": 92, "##4": 93, "##\u00ea": 94, "##\u0114": 95, "##\u0142": 96, "##l": 97, "##\u00a2": 98, "##'": 99, "##1": 100, "##\u012e": 101, "##M": 102, "##Z": 103, "##y": 104, "##\u00bc": 105, "##\u00c7": 106, "##\u00af": 107, "##p": 108, "##\u00cc": 109, "##*": 110, "##\u00d4": 111, "##0": 112, "##\u00fd": 113, "##\u00d1": 114, "##\u00dc": 115, "##\u00ec": 116, "##\u00ac": 117, "##\u0130": 118, "##\u00e4": 119, "##\u00d3": 120, "##\u00ed": 121, "##E": 122, "##\u00d7": 123, "##\u0139": 124, "##9": 125, "##\u0128": 126, "##m": 127, "##\u00fb": 128, "##P": 129, "##`": 130, "##3": 131, "##\u00f4": 132, "##\u00c8": 133, "##G": 134, "##\u00a8": 135, "##$": 136, "##J": 137, "##u": 138, "##~": 139, "##\u0124": 140, "##\u0126": 141, "##\u0129": 142, "##6": 143, "##>": 144, "##\u00ce": 145, "##\u0143": 146, "##\u00f3": 147, "##&": 148, "##.": 149, "##\u00a6": 150, "##=": 151, "##\u00aa": 152, "##\u010b": 153, "##\u00e6": 154, "##7": 155, "##8": 156, "##d": 157, "##\u00b1": 158, "##\u0131": 159, "##\u00e8": 160, "##\u0141": 161, "##\u00c2": 162, "##2": 163, "##\u00c4": 164, "##\u0116": 165, "##h": 166, "##\u00a4": 167, "##R": 168, "##\u013f": 169, "##x": 170, "##?": 171, "##\u0119": 172, "##z": 173, "##\u0140": 174, "##]": 175, "##,": 176, "##+": 177, "##|": 178, "##\u0121": 179, "##\u010a": 180, "##\u00ae": 181, "##g": 182, "##\u0103": 183, "##\u00b3": 184, "##\u0138": 185, "##\u0123": 186, "##\u00a9": 187, "##\u00f9": 188, "##N": 189, "##o": 190, "##t": 191, "##U": 192, "##\u0110": 193, "##\u0100": 194, "##\u00ba": 195, "##\u0137": 196, "##b": 197, "##B": 198, "##j": 199, "##\u00d9": 200, "##q": 201, "##\u00f2": 202, "##\u0102": 203, "##\u0133": 204, "##\u00f8": 205, "##\u00da": 206, "##\u011d": 207, "##\u011e": 208, "##S": 209, "##H": 210, "##Q": 211, "##s": 212, "##\u010f": 213, "##\u0136": 214, "##\u00bd": 215, "##5": 216, "##L": 217, "##\u0115": 218, "##@": 219, "##!": 220, "##\u0107": 221, "##\u00e1": 222, "##\\": 223, "##\u0134": 224, "##\u013c": 225, "##\u00c1": 226, "##^": 227, "##\u00bb": 228, "##\u00c9": 229, "##\u00d8": 230, "##\u0108": 231, "##F": 232, "##\u00cb": 233, "##\u011b": 234, "##\u012b": 235, "##n": 236, "##\u00b0": 237, "##<": 238, "##\u00e0": 239, "##\u0113": 240, "##\u0120": 241, "##\u012c": 242, "##O": 243, "##D": 244, "##\u00c5": 245, "##\u0127": 246, "##c": 247, "##\u00cd": 248, "##A": 249, "##a": 250, "##K": 251, "##\u00ca": 252, "##\u0106": 253, "##\u0104": 254, "##\u00eb": 255, "##\u00b5": 256, "##w": 257, "##\u00b7": 258, "##\u0111": 259, "##ng": 260, "##er": 261, "##\ufffd": 262, "##ent": 263, "##on": 264, "##nt": 265, "##en": 266, "##her": 267, "##al": 268, "##ct": 269, "##nd": 270, "##ion": 271, "##in": 272, "##es": 273, "##th": 274, "##at": 275, "##le": 276, "##gh": 277, "##or": 278, "##ss": 279, "##ar": 280, "##ld": 281, "##ur": 282, "##ch": 283, "##ou": 284, "##re": 285, "##ti": 286, "##us": 287, "##st": 288, "##se": 289, "##ge": 290, "##ht": 291, "## ": 292, "##ut": 293, "##ing": 294, "##ple": 295, "##me": 296, "##ul": 297, "##tion": 298, "##om": 299, "##an": 300, "##ic": 301, "##ce": 302, "##em": 303, "##ra": 304, "##ess": 305, "##og": 306, "##it": 307, "##el": 308, "##rt": 309, "##uc": 310, "##ve": 311, "##ne": 312, "##ue": 313, "##te": 314, "##ay": 315, "##lt": 316, "##ow": 317, "##il": 318, "##rd": 319, "##ment": 320, "##bl": 321, "##ect": 322, "##ma": 323, "##ed": 324, "##de": 325, "##et": 326, "##is": 327, "##ll": 328, "##ver": 329, "##ri": 330, "##tem": 331, "##ud": 332, "##ase": 333, "##use": 334, "##io": 335, "##ad": 336, "##rg": 337, "##nc": 338, "##rch": 339, "##li": 340, "##ip": 341, "##ly": 342, "##id": 343, "##la": 344, "##ugh": 345, "##nce": 346, "##rn": 347, "##ter": 348, "##rm": 349, "##ia": 350, "##and": 351, "##ear": 352, "##as": 353, "##ag": 354, "##ate": 355, "##tr": 356, "##he": 357, "##od": 358, "##ni": 359, "##ty": 360, "##ght": 361, "##und": 362, "##ta": 363, "##lop": 364, "##ore": 365, "##si": 366, "##gn": 367, "##iv": 368, "##sh": 369, "##ol": 370, "##lo": 371, "##tor": 372, "##ber": 373, "##pl": 374, "##un": 375, "##ph": 376, "##rk": 377, "##een": 378, "##ry": 379, "##ard": 380, "##out": 381, "##rat": 382, "##oy": 383, "##ro": 384, "##ith": 385, "##lit": 386, "##\ufffd\ufffd": 387, "##ther": 388, "##ib": 389, "##ure": 390, "##lf": 391, "##ck": 392, "##mat": 393, "##ish": 394, "##ial": 395, "##rc": 396, "##ec": 397, "##ca": 398, "##ork": 399, "##tu": 400, "##est": 401, "##mal": 402, "##os": 403, "##den": 404, "##ee": 405, "##dy": 406, "##age": 407, "##stem": 408, "##ation": 409, "##ke": 410, "##am": 411, "##na": 412, "##to": 413, "##ua": 414, "##ain": 415, "##pt": 416, "##lem": 417, "##ui": 418, "##ous": 419, "##are": 420, "##ult": 421, "##di": 422, "##ween": 423, "##we": 424, "##iat": 425, "##ding": 426, "##pa": 427, "##arch": 428, "##ough": 429, "##tur": 430, "##ine": 431, "##lar": 432, "##uen": 433, "##ional": 434, "##lly": 435, "##mple": 436, "##men": 437, "##ltur": 438, "##sue": 439, "##ays": 440, "##op": 441, "##ble": 442, "##ant": 443, "##um": 444, "##wer": 445, "##ci": 446, "##rce": 447, "##ood": 448, "##ether": 449, "##mber": 450, "##tio": 451, "##log": 452, "##ga": 453, "##cer": 454, "##br": 455, "##rv": 456, "##sk": 457, "##elf": 458, "##ap": 459, "##mp": 460, "##ac": 461, "##fe": 462, "##ot": 463, "##ity": 464, "##sion": 465, "##ati": 466, "##tp": 467, "##cl": 468, "##ir": 469, "##mi": 470, "##ness": 471, "##oo": 472, "##has": 473, "##mb": 474, "##vi": 475, "##cat": 476, "##nk": 477, "##ea": 478, "##up": 479, "##ey": 480, "##end": 481, "##rica": 482, "##ally": 483, "##ho": 484, "##ack": 485, "##tal": 486, "##tic": 487, "##but": 488, "##ral": 489, "##lat": 490, "##ive": 491, "##ere": 492, "##ady": 493, "##vel": 494, "##ek": 495, "##ond": 496, "##be": 497, "##ace": 498, "##ria": 499, "##rs": 500, "##nat": 501, "##tan": 502, "##tra": 503, "##ov": 504, "##der": 505, "##era": 506, "##cult": 507, "##tant": 508, "##ram": 509, "##fi": 510, "##rse": 511, "##ug": 512, "##ition": 513, "##ort": 514, "##ha": 515, "##no": 516, "##ie": 517, "##oss": 518, "##ciat": 519, "##rder": 520, "##ark": 521, "##mati": 522, "##eo": 523, "##iro": 524, "##enc": 525, "##ted": 526, "##ime": 527, "##ell": 528, "##ual": 529, "##tom": 530, "##avio": 531, "##wn": 532, "##red": 533, "##nu": 534, "##fic": 535, "##hool": 536, "##ab": 537, "##gl": 538, "##ep": 539, "##mph": 540, "##unt": 541, "##ig": 542, "##ide": 543, "##nal": 544, "##pe": 545, "##va": 546, "##eas": 547, "##ger": 548, "##gu": 549, "##eri": 550, "##cti": 551, "##nos": 552, "##ause": 553, "##nti": 554, "##cle": 555, "##av": 556, "##hin": 557, "##ps": 558, "##eady": 559, "##dent": 560, "##ite": 561, "##ture": 562, "##ool": 563, "##ka": 564, "##dia": 565, "##cul": 566, "##oom": 567, "##all": 568, "##po": 569, "##rld": 570, "##act": 571, "##str": 572, "##ys": 573, "##pen": 574, "##ost": 575, "##ok": 576, "##man": 577, "##yle": 578, "##ale": 579, "##ill": 580, "##ultur": 581, "##int": 582, "##ula": 583, "##eight": 584, "##qu": 585, "##rag": 586, "##let": 587, "##im": 588, "##ns": 589, "##min": 590, "##anc": 591, "##bit": 592, "##ien": 593, "##per": 594, "##gra": 595, "##ew": 596, "##ev": 597, "##trat": 598, "##hing": 599}