Skip to content

Commit 8e52042

Browse files
add tokenizer model and tokenizer tests
1 parent 5f78e18 commit 8e52042

File tree

3 files changed

+158
-0
lines changed

3 files changed

+158
-0
lines changed

models/ggml-vocab-mellum.gguf

3.34 MB
Binary file not shown.

models/ggml-vocab-mellum.gguf.inp

Lines changed: 112 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,112 @@
1+
ied 4 ½ months
2+
__ggml_vocab_test__
3+
Äpfel
4+
__ggml_vocab_test__
5+
6+
__ggml_vocab_test__
7+
8+
__ggml_vocab_test__
9+
10+
__ggml_vocab_test__
11+
12+
__ggml_vocab_test__
13+
14+
__ggml_vocab_test__
15+
16+
17+
__ggml_vocab_test__
18+
19+
20+
21+
__ggml_vocab_test__
22+
23+
24+
25+
26+
__ggml_vocab_test__
27+
28+
29+
__ggml_vocab_test__
30+
Hello world
31+
__ggml_vocab_test__
32+
Hello world
33+
__ggml_vocab_test__
34+
Hello World
35+
__ggml_vocab_test__
36+
Hello World
37+
__ggml_vocab_test__
38+
Hello World!
39+
__ggml_vocab_test__
40+
Hello, world!
41+
__ggml_vocab_test__
42+
Hello, world!
43+
__ggml_vocab_test__
44+
this is 🦙.cpp
45+
__ggml_vocab_test__
46+
w048 7tuijk dsdfhu
47+
__ggml_vocab_test__
48+
нещо на Български
49+
__ggml_vocab_test__
50+
កាន់តែពិសេសអាចខលចេញ
51+
__ggml_vocab_test__
52+
🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)
53+
__ggml_vocab_test__
54+
Hello
55+
__ggml_vocab_test__
56+
Hello
57+
__ggml_vocab_test__
58+
Hello
59+
__ggml_vocab_test__
60+
Hello
61+
__ggml_vocab_test__
62+
Hello
63+
__ggml_vocab_test__
64+
Hello
65+
Hello
66+
__ggml_vocab_test__
67+
(
68+
__ggml_vocab_test__
69+
70+
=
71+
__ggml_vocab_test__
72+
' era
73+
__ggml_vocab_test__
74+
Hello, y'all! How are you 😁 ?我想在apple工作1314151天~
75+
__ggml_vocab_test__
76+
!!!!!!
77+
__ggml_vocab_test__
78+
3
79+
__ggml_vocab_test__
80+
33
81+
__ggml_vocab_test__
82+
333
83+
__ggml_vocab_test__
84+
3333
85+
__ggml_vocab_test__
86+
33333
87+
__ggml_vocab_test__
88+
333333
89+
__ggml_vocab_test__
90+
3333333
91+
__ggml_vocab_test__
92+
33333333
93+
__ggml_vocab_test__
94+
333333333
95+
__ggml_vocab_test__
96+
Cửa Việt
97+
__ggml_vocab_test__
98+
discards
99+
__ggml_vocab_test__
100+
101+
102+
103+
104+
105+
106+
107+
108+
109+
110+
111+
🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天~ ------======= нещо на Български ''''''```````""""......!!!!!!?????? I've been 'told he's there, 'RE you sure? 'M not sure I'll make it, 'D you like some tea? We'Ve a'lL
112+
__ggml_vocab_test__

models/ggml-vocab-mellum.gguf.out

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
1743 775 4588 148 9225
2+
49822 10221 332
3+
4+
247
5+
247 247
6+
247 247 247
7+
224
8+
225
9+
225 225
10+
225 225 225
11+
2572
12+
10626 3822
13+
19762 3822
14+
10626 8098
15+
19762 8098
16+
19762 8098 27
17+
10626 38 3822 27
18+
19762 38 3822 27
19+
520 432 8892 126 274 40 2354
20+
113 18619 1345 42961 17444 6729 1714 4590
21+
30813 7682 834 8413 33028 13043 1719 6391 9791 29827
22+
33595 25149 31055 51151 43497 78271 66809 58451 37263 66436 37263 65068 25149 65088 5367 250 47929 65088 66436 90924
23+
61661 249 341 4111 35 26591 141 19340 68052 131 20565 341 15611 350 69572 72291 35 62765 341 5935 39662 569 1202 2027 4174 3961 35
24+
10626
25+
19762
26+
247 19762
27+
247 247 19762
28+
247 247 247 19762
29+
247 247 247 19762 225 247 247 247 19762
30+
341
31+
225 306
32+
33 24747
33+
10626 38 437 33 474 27 6863 748 691 26591 250 1364 91890 3038 10123 18854 45990 10408 10742 41579
34+
12525 3740
35+
45
36+
592
37+
9476
38+
1882
39+
34333
40+
3586
41+
33390
42+
17892
43+
17892 45
44+
61 40968 91 10788 79508
45+
936 16228
46+
225 493 225 493 225 225 34362 3787 2572 722 948 984 247 247 247 247 247 225 61661 249 341 4111 35 26591 141 19340 68052 131 20565 341 15611 350 69572 72291 35 62765 8892 126 274 4641 126 274 690 4875 49633 247 1882 247 34333 247 3586 247 33390 247 17892 690 40 45 690 502 45 690 1366 45 247 33595 25149 31055 51151 43497 78271 66809 58451 37263 66436 37263 65068 25149 65088 40837 250 1364 91890 3038 10123 18854 45990 10408 10742 41579 31166 21059 11927 7682 834 8413 33028 13043 1719 6391 9791 29827 3638 32208 21001 1305 17155 29835 12525 3740 22922 8061 391 6070 1962 382 298 1061 633 1151 1828 38 382 736 691 4076 57 382 71 654 4076 391 5906 1773 650 38 382 62 691 1893 1475 7939 57 2168 33 4314 283 33 102 70

0 commit comments

Comments
 (0)