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,
|
| 3 |
-
1000,
|
| 4 |
-
2000,
|
| 5 |
-
3000,
|
| 6 |
-
4000,
|
| 7 |
-
5000,
|
| 8 |
-
6000,
|
| 9 |
-
7000,
|
| 10 |
-
8000,
|
| 11 |
-
9000,
|
| 12 |
-
10000,
|
| 13 |
-
11000,
|
| 14 |
-
12000,
|
| 15 |
-
13000,
|
| 16 |
-
14000,
|
| 17 |
-
15000,
|
| 18 |
-
16000,
|
| 19 |
-
17000,
|
| 20 |
-
18000,
|
| 21 |
-
19000,
|
| 22 |
-
20000,
|
| 23 |
-
21000,
|
| 24 |
-
22000,
|
| 25 |
-
23000,
|
| 26 |
-
24000,
|
| 27 |
-
25000,
|
| 28 |
-
26000,
|
| 29 |
-
27000,
|
| 30 |
-
28000,
|
| 31 |
-
29000,
|
| 32 |
-
30000,
|
| 33 |
-
31000,
|
| 34 |
-
32000,
|
| 35 |
-
33000,
|
| 36 |
-
34000,
|
| 37 |
-
35000,
|
| 38 |
-
36000,
|
| 39 |
-
37000,
|
| 40 |
-
38000,
|
| 41 |
-
39000,
|
| 42 |
-
40000,
|
| 43 |
-
41000,
|
| 44 |
-
42000,
|
| 45 |
-
43000,
|
| 46 |
-
44000,
|
| 47 |
-
45000,
|
| 48 |
-
46000,
|
| 49 |
-
47000,
|
| 50 |
-
48000,
|
| 51 |
-
49000,
|
| 52 |
-
50000,
|
| 53 |
-
51000,
|
| 54 |
-
52000,
|
| 55 |
-
53000,
|
| 56 |
-
54000,
|
| 57 |
-
55000,
|
| 58 |
-
56000,
|
| 59 |
-
57000,
|
| 60 |
-
58000,
|
| 61 |
-
59000,
|
| 62 |
-
60000,
|
| 63 |
-
61000,
|
| 64 |
-
62000,
|
| 65 |
-
63000,
|
| 66 |
-
64000,
|
| 67 |
-
65000,
|
| 68 |
-
66000,
|
| 69 |
-
67000,
|
| 70 |
-
68000,
|
| 71 |
-
69000,
|
| 72 |
-
70000,
|
| 73 |
-
71000,
|
| 74 |
-
72000,
|
| 75 |
-
73000,
|
| 76 |
-
74000,
|
| 77 |
-
75000,
|
| 78 |
-
76000,
|
| 79 |
-
77000,
|
| 80 |
-
78000,
|
| 81 |
-
79000,
|
| 82 |
-
80000,
|
| 83 |
-
81000,
|
| 84 |
-
82000,
|
| 85 |
-
83000,
|
| 86 |
-
84000,
|
| 87 |
-
85000,
|
| 88 |
-
86000,
|
| 89 |
-
87000,
|
| 90 |
-
88000,
|
| 91 |
-
89000,
|
| 92 |
-
90000,
|
| 93 |
-
91000,
|
| 94 |
-
92000,
|
| 95 |
-
93000,
|
| 96 |
-
94000,
|
| 97 |
-
95000,
|
| 98 |
-
96000,
|
| 99 |
-
97000,
|
| 100 |
-
98000,
|
| 101 |
-
99000,
|
| 102 |
-
100000,
|
| 103 |
-
101000,
|
| 104 |
-
102000,
|
| 105 |
-
103000,
|
| 106 |
-
104000,
|
| 107 |
-
105000,
|
| 108 |
-
106000,
|
| 109 |
-
107000,
|
| 110 |
-
108000,
|
| 111 |
-
109000,
|
| 112 |
-
110000,
|
| 113 |
-
111000,
|
| 114 |
-
112000,
|
| 115 |
-
113000,
|
| 116 |
-
114000,
|
| 117 |
-
115000,
|
| 118 |
-
116000,
|
| 119 |
-
117000,
|
| 120 |
-
118000,
|
| 121 |
-
119000,
|
| 122 |
-
120000,
|
| 123 |
-
121000,
|
| 124 |
-
122000,
|
| 125 |
-
123000,
|
| 126 |
-
124000,
|
| 127 |
-
125000,
|
| 128 |
-
126000,
|
| 129 |
-
127000,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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":
|
| 26 |
"content": "<|unk|>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
|
@@ -65,604 +65,603 @@
|
|
| 65 |
"vocab": {
|
| 66 |
"<|padding|>": 0,
|
| 67 |
"<|endoftext|>": 1,
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"
|
| 93 |
-
"
|
| 94 |
-
"
|
| 95 |
-
"
|
| 96 |
-
"
|
| 97 |
-
"
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"
|
| 103 |
-
"
|
| 104 |
-
"
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"
|
| 108 |
-
"
|
| 109 |
-
"
|
| 110 |
-
"
|
| 111 |
-
"
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
"
|
| 115 |
-
"
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
-
"
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
"
|
| 135 |
-
"
|
| 136 |
-
"
|
| 137 |
-
"
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
"
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"
|
| 148 |
-
"
|
| 149 |
-
"
|
| 150 |
-
"
|
| 151 |
-
"
|
| 152 |
-
"
|
| 153 |
-
"
|
| 154 |
-
"
|
| 155 |
-
"
|
| 156 |
-
"
|
| 157 |
-
"
|
| 158 |
-
"
|
| 159 |
-
"
|
| 160 |
-
"
|
| 161 |
-
"
|
| 162 |
-
"
|
| 163 |
-
"
|
| 164 |
-
"
|
| 165 |
-
"
|
| 166 |
-
"
|
| 167 |
-
"
|
| 168 |
-
"
|
| 169 |
-
"
|
| 170 |
-
"
|
| 171 |
-
"
|
| 172 |
-
"
|
| 173 |
-
"
|
| 174 |
-
"
|
| 175 |
-
"
|
| 176 |
-
"
|
| 177 |
-
"
|
| 178 |
-
"
|
| 179 |
-
"
|
| 180 |
-
"
|
| 181 |
-
"
|
| 182 |
-
"
|
| 183 |
-
"
|
| 184 |
-
"
|
| 185 |
-
"
|
| 186 |
-
"
|
| 187 |
-
"
|
| 188 |
-
"
|
| 189 |
-
"
|
| 190 |
-
"
|
| 191 |
-
"
|
| 192 |
-
"
|
| 193 |
-
"
|
| 194 |
-
"
|
| 195 |
-
"
|
| 196 |
-
"
|
| 197 |
-
"
|
| 198 |
-
"
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"
|
| 202 |
-
"
|
| 203 |
-
"
|
| 204 |
-
"
|
| 205 |
-
"
|
| 206 |
-
"
|
| 207 |
-
"
|
| 208 |
-
"
|
| 209 |
-
"
|
| 210 |
-
"
|
| 211 |
-
"
|
| 212 |
-
"
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"
|
| 216 |
-
"
|
| 217 |
-
"
|
| 218 |
-
"
|
| 219 |
-
"
|
| 220 |
-
"
|
| 221 |
-
"
|
| 222 |
-
"
|
| 223 |
-
"
|
| 224 |
-
"
|
| 225 |
-
"
|
| 226 |
-
"
|
| 227 |
-
"
|
| 228 |
-
"
|
| 229 |
-
"
|
| 230 |
-
"
|
| 231 |
-
"
|
| 232 |
-
"
|
| 233 |
-
"
|
| 234 |
-
"
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
| 238 |
-
"
|
| 239 |
-
"
|
| 240 |
-
"
|
| 241 |
-
"
|
| 242 |
-
"
|
| 243 |
-
"
|
| 244 |
-
"
|
| 245 |
-
"
|
| 246 |
-
"
|
| 247 |
-
"
|
| 248 |
-
"
|
| 249 |
-
"
|
| 250 |
-
"
|
| 251 |
-
"
|
| 252 |
-
"
|
| 253 |
-
"
|
| 254 |
-
"
|
| 255 |
-
"
|
| 256 |
-
"
|
| 257 |
-
"
|
| 258 |
-
"
|
| 259 |
-
"
|
| 260 |
-
"
|
| 261 |
-
"
|
| 262 |
-
"
|
| 263 |
-
"
|
| 264 |
-
"
|
| 265 |
-
"
|
| 266 |
-
"
|
| 267 |
-
"
|
| 268 |
-
"
|
| 269 |
-
"
|
| 270 |
-
"
|
| 271 |
-
"
|
| 272 |
-
"
|
| 273 |
-
"
|
| 274 |
-
"
|
| 275 |
-
"
|
| 276 |
-
"
|
| 277 |
-
"
|
| 278 |
-
"
|
| 279 |
-
"
|
| 280 |
-
"
|
| 281 |
-
"
|
| 282 |
-
"
|
| 283 |
-
"
|
| 284 |
-
"
|
| 285 |
-
"
|
| 286 |
-
"
|
| 287 |
-
"
|
| 288 |
-
"
|
| 289 |
-
"
|
| 290 |
-
"
|
| 291 |
-
"
|
| 292 |
-
"
|
| 293 |
-
"
|
| 294 |
-
"
|
| 295 |
-
"
|
| 296 |
-
"
|
| 297 |
-
"
|
| 298 |
-
"
|
| 299 |
-
"
|
| 300 |
-
"
|
| 301 |
-
"
|
| 302 |
-
"
|
| 303 |
-
"
|
| 304 |
-
"
|
| 305 |
-
"
|
| 306 |
-
"
|
| 307 |
-
"
|
| 308 |
-
"
|
| 309 |
-
"
|
| 310 |
-
"
|
| 311 |
-
"
|
| 312 |
-
"
|
| 313 |
-
"
|
| 314 |
-
"
|
| 315 |
-
"
|
| 316 |
-
"
|
| 317 |
-
"
|
| 318 |
-
"
|
| 319 |
-
"
|
| 320 |
-
"
|
| 321 |
-
"
|
| 322 |
-
"
|
| 323 |
-
"
|
| 324 |
-
"
|
| 325 |
-
"##
|
| 326 |
-
"
|
| 327 |
-
"
|
| 328 |
-
"
|
| 329 |
-
"
|
| 330 |
-
"
|
| 331 |
-
"##
|
| 332 |
-
"##
|
| 333 |
-
"
|
| 334 |
-
"
|
| 335 |
-
"##
|
| 336 |
-
"##
|
| 337 |
-
"
|
| 338 |
-
"##
|
| 339 |
-
"##
|
| 340 |
-
"
|
| 341 |
-
"
|
| 342 |
-
"
|
| 343 |
-
"
|
| 344 |
-
"
|
| 345 |
-
"##
|
| 346 |
-
"
|
| 347 |
-
"
|
| 348 |
-
"
|
| 349 |
-
"
|
| 350 |
-
"
|
| 351 |
-
"
|
| 352 |
-
"##
|
| 353 |
-
"
|
| 354 |
-
"
|
| 355 |
-
"
|
| 356 |
-
"
|
| 357 |
-
"
|
| 358 |
-
"##
|
| 359 |
-
"
|
| 360 |
-
"##
|
| 361 |
-
"
|
| 362 |
-
"
|
| 363 |
-
"##
|
| 364 |
-
"##
|
| 365 |
-
"
|
| 366 |
-
"##
|
| 367 |
-
"##
|
| 368 |
-
"
|
| 369 |
-
"##
|
| 370 |
-
"
|
| 371 |
-
"
|
| 372 |
-
"
|
| 373 |
-
"##
|
| 374 |
-
"##
|
| 375 |
-
"##
|
| 376 |
-
"##
|
| 377 |
-
"##
|
| 378 |
-
"
|
| 379 |
-
"
|
| 380 |
-
"
|
| 381 |
-
"
|
| 382 |
-
"
|
| 383 |
-
"
|
| 384 |
-
"##
|
| 385 |
-
"##
|
| 386 |
-
"
|
| 387 |
-
"##
|
| 388 |
-
"
|
| 389 |
-
"
|
| 390 |
-
"
|
| 391 |
-
"##
|
| 392 |
-
"
|
| 393 |
-
"
|
| 394 |
-
"
|
| 395 |
-
"
|
| 396 |
-
"##
|
| 397 |
-
"##
|
| 398 |
-
"
|
| 399 |
-
"
|
| 400 |
-
"##
|
| 401 |
-
"##
|
| 402 |
-
"
|
| 403 |
-
"##
|
| 404 |
-
"##
|
| 405 |
-
"##
|
| 406 |
-
"
|
| 407 |
-
"
|
| 408 |
-
"
|
| 409 |
-
"
|
| 410 |
-
"
|
| 411 |
-
"
|
| 412 |
-
"##
|
| 413 |
-
"
|
| 414 |
-
"
|
| 415 |
-
"
|
| 416 |
-
"##
|
| 417 |
-
"##
|
| 418 |
-
"##
|
| 419 |
-
"
|
| 420 |
-
"
|
| 421 |
-
"
|
| 422 |
-
"
|
| 423 |
-
"
|
| 424 |
-
"
|
| 425 |
-
"
|
| 426 |
-
"
|
| 427 |
-
"
|
| 428 |
-
"
|
| 429 |
-
"
|
| 430 |
-
"##
|
| 431 |
-
"
|
| 432 |
-
"
|
| 433 |
-
"
|
| 434 |
-
"##
|
| 435 |
-
"
|
| 436 |
-
"
|
| 437 |
-
"
|
| 438 |
-
"
|
| 439 |
-
"
|
| 440 |
-
"
|
| 441 |
-
"
|
| 442 |
-
"
|
| 443 |
-
"
|
| 444 |
-
"
|
| 445 |
-
"
|
| 446 |
-
"
|
| 447 |
-
"##
|
| 448 |
-
"
|
| 449 |
-
"
|
| 450 |
-
"##
|
| 451 |
-
"
|
| 452 |
-
"
|
| 453 |
-
"##
|
| 454 |
-
"
|
| 455 |
-
"
|
| 456 |
-
"
|
| 457 |
-
"
|
| 458 |
-
"
|
| 459 |
-
"
|
| 460 |
-
"
|
| 461 |
-
"##
|
| 462 |
-
"
|
| 463 |
-
"
|
| 464 |
-
"
|
| 465 |
-
"
|
| 466 |
-
"
|
| 467 |
-
"##
|
| 468 |
-
"
|
| 469 |
-
"
|
| 470 |
-
"
|
| 471 |
-
"
|
| 472 |
-
"
|
| 473 |
-
"##
|
| 474 |
-
"##
|
| 475 |
-
"
|
| 476 |
-
"
|
| 477 |
-
"
|
| 478 |
-
"
|
| 479 |
-
"##
|
| 480 |
-
"
|
| 481 |
-
"
|
| 482 |
-
"
|
| 483 |
-
"##
|
| 484 |
-
"
|
| 485 |
-
"
|
| 486 |
-
"##
|
| 487 |
-
"
|
| 488 |
-
"
|
| 489 |
-
"
|
| 490 |
-
"
|
| 491 |
-
"##
|
| 492 |
-
"
|
| 493 |
-
"
|
| 494 |
-
"
|
| 495 |
-
"
|
| 496 |
-
"
|
| 497 |
-
"##
|
| 498 |
-
"
|
| 499 |
-
"
|
| 500 |
-
"
|
| 501 |
-
"
|
| 502 |
-
"##
|
| 503 |
-
"##
|
| 504 |
-
"
|
| 505 |
-
"##
|
| 506 |
-
"
|
| 507 |
-
"##
|
| 508 |
-
"
|
| 509 |
-
"
|
| 510 |
-
"##
|
| 511 |
-
"
|
| 512 |
-
"##
|
| 513 |
-
"
|
| 514 |
-
"
|
| 515 |
-
"
|
| 516 |
-
"##
|
| 517 |
-
"
|
| 518 |
-
"
|
| 519 |
-
"
|
| 520 |
-
"
|
| 521 |
-
"##
|
| 522 |
-
"##
|
| 523 |
-
"
|
| 524 |
-
"
|
| 525 |
-
"
|
| 526 |
-
"
|
| 527 |
-
"##
|
| 528 |
-
"
|
| 529 |
-
"
|
| 530 |
-
"##
|
| 531 |
-
"
|
| 532 |
-
"
|
| 533 |
-
"
|
| 534 |
-
"
|
| 535 |
-
"
|
| 536 |
-
"
|
| 537 |
-
"
|
| 538 |
-
"
|
| 539 |
-
"
|
| 540 |
-
"##
|
| 541 |
-
"
|
| 542 |
-
"
|
| 543 |
-
"
|
| 544 |
-
"
|
| 545 |
-
"
|
| 546 |
-
"
|
| 547 |
-
"
|
| 548 |
-
"
|
| 549 |
-
"
|
| 550 |
-
"
|
| 551 |
-
"
|
| 552 |
-
"
|
| 553 |
-
"
|
| 554 |
-
"
|
| 555 |
-
"
|
| 556 |
-
"
|
| 557 |
-
"##
|
| 558 |
-
"##
|
| 559 |
-
"##
|
| 560 |
-
"
|
| 561 |
-
"
|
| 562 |
-
"##
|
| 563 |
-
"
|
| 564 |
-
"
|
| 565 |
-
"##
|
| 566 |
-
"
|
| 567 |
-
"
|
| 568 |
-
"
|
| 569 |
-
"##
|
| 570 |
-
"
|
| 571 |
-
"
|
| 572 |
-
"
|
| 573 |
-
"
|
| 574 |
-
"
|
| 575 |
-
"
|
| 576 |
-
"##
|
| 577 |
-
"
|
| 578 |
-
"
|
| 579 |
-
"##
|
| 580 |
-
"
|
| 581 |
-
"##
|
| 582 |
-
"
|
| 583 |
-
"##
|
| 584 |
-
"##
|
| 585 |
-
"##
|
| 586 |
-
"##
|
| 587 |
-
"##
|
| 588 |
-
"##
|
| 589 |
-
"##
|
| 590 |
-
"##
|
| 591 |
-
"##
|
| 592 |
-
"##
|
| 593 |
-
"##
|
| 594 |
-
"##
|
| 595 |
-
"##
|
| 596 |
-
"##
|
| 597 |
-
"##
|
| 598 |
-
"##
|
| 599 |
-
"##
|
| 600 |
-
"##
|
| 601 |
-
"##
|
| 602 |
-
"##
|
| 603 |
-
"##
|
| 604 |
-
"##
|
| 605 |
-
"##
|
| 606 |
-
"##
|
| 607 |
-
"##
|
| 608 |
-
"##
|
| 609 |
-
"##
|
| 610 |
-
"##
|
| 611 |
-
"##
|
| 612 |
-
"##
|
| 613 |
-
"##
|
| 614 |
-
"##
|
| 615 |
-
"##
|
| 616 |
-
"##
|
| 617 |
-
"##
|
| 618 |
-
"##
|
| 619 |
-
"##
|
| 620 |
-
"##
|
| 621 |
-
"##
|
| 622 |
-
"##
|
| 623 |
-
"##
|
| 624 |
-
"##
|
| 625 |
-
"##
|
| 626 |
-
"##
|
| 627 |
-
"##
|
| 628 |
-
"##
|
| 629 |
-
"##
|
| 630 |
-
"##
|
| 631 |
-
"##
|
| 632 |
-
"##
|
| 633 |
-
"##
|
| 634 |
-
"##
|
| 635 |
-
"##
|
| 636 |
-
"##
|
| 637 |
-
"##
|
| 638 |
-
"##
|
| 639 |
-
"##
|
| 640 |
-
"##
|
| 641 |
-
"##
|
| 642 |
-
"##
|
| 643 |
-
"##
|
| 644 |
-
"##
|
| 645 |
-
"##
|
| 646 |
-
"##
|
| 647 |
-
"##
|
| 648 |
-
"##
|
| 649 |
-
"##
|
| 650 |
-
"##
|
| 651 |
-
"##
|
| 652 |
-
"##
|
| 653 |
-
"##
|
| 654 |
-
"##
|
| 655 |
-
"##
|
| 656 |
-
"##
|
| 657 |
-
"##
|
| 658 |
-
"##
|
| 659 |
-
"##
|
| 660 |
-
"##
|
| 661 |
-
"##
|
| 662 |
-
"##
|
| 663 |
-
"##
|
| 664 |
-
"##
|
| 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 |
-
"
|
| 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 |
-
{"
|
|
|
|
| 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}
|