Skip to content

tests : improve UGM tokenizer test coverage #13773

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 25, 2025
Merged

tests : improve UGM tokenizer test coverage #13773

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
92929da
add nomic-bert-moe vocab test files
CISC May 25, 2025
ed321ea
add test-tokenizer-0-nomic-bert-moe
CISC May 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added models/ggml-vocab-nomic-bert-moe.gguf
View file
Open in desktop
Binary file not shown.
112 changes: 112 additions & 0 deletions models/ggml-vocab-nomic-bert-moe.gguf.inp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,112 @@
ied 4 ½ months
__ggml_vocab_test__
Führer
__ggml_vocab_test__

__ggml_vocab_test__

__ggml_vocab_test__

__ggml_vocab_test__

__ggml_vocab_test__

__ggml_vocab_test__


__ggml_vocab_test__



__ggml_vocab_test__




__ggml_vocab_test__


__ggml_vocab_test__
Hello world
__ggml_vocab_test__
Hello world
__ggml_vocab_test__
Hello World
__ggml_vocab_test__
Hello World
__ggml_vocab_test__
Hello World!
__ggml_vocab_test__
Hello, world!
__ggml_vocab_test__
Hello, world!
__ggml_vocab_test__
this is 🦙.cpp
__ggml_vocab_test__
w048 7tuijk dsdfhu
__ggml_vocab_test__
нещо на Български
__ggml_vocab_test__
កាន់តែពិសេសអាចខលចេញ
__ggml_vocab_test__
🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)
__ggml_vocab_test__
Hello
__ggml_vocab_test__
Hello
__ggml_vocab_test__
Hello
__ggml_vocab_test__
Hello
__ggml_vocab_test__
Hello
__ggml_vocab_test__
Hello
Hello
__ggml_vocab_test__
(
__ggml_vocab_test__

=
__ggml_vocab_test__
' era
__ggml_vocab_test__
Hello, y'all! How are you 😁 ?我想在apple工作1314151天～
__ggml_vocab_test__
!!!!!!
__ggml_vocab_test__
3
__ggml_vocab_test__
33
__ggml_vocab_test__
333
__ggml_vocab_test__
3333
__ggml_vocab_test__
33333
__ggml_vocab_test__
333333
__ggml_vocab_test__
3333333
__ggml_vocab_test__
33333333
__ggml_vocab_test__
333333333
__ggml_vocab_test__
Cửa Việt
__ggml_vocab_test__
discards
__ggml_vocab_test__











🚀 (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
__ggml_vocab_test__
46 changes: 46 additions & 0 deletions models/ggml-vocab-nomic-bert-moe.gguf.out
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
17 297 201 78660 21775
72805 4097 56









35378 8999
35378 8999
35378 6661
35378 6661
35378 6661 38
35378 4 8999 38
35378 4 8999 38
903 83 6 3 5 238 6366
148 7709 1019 361 458 134362 104 7 71 420 1132
14271 29 117152
6 149561 78270 48967 64254 7616 81705
6 247206 15 33176 16 6 247442 6 3 15755 15 144227 8705 18255 40292 158 4460 33 27686 16 6 142325 15 191 538 28 121505 450 1556 6863 10002 47 1098 16
35378
35378
35378
35378
35378
35378 35378
15
2203
242 1615
35378 4 113 25 5584 38 11249 621 398 6 201344 705 23638 213 9007 133 1879 2681 2592 135224 1906 6087
6 90827
138
3912
6 66000
138 66000
3912 66000
6 66000 66000
138 66000 66000
3912 66000 66000
6 66000 66000 66000
199152 3763
17116 99397
6 247206 15 33176 16 6 247442 6 3 15755 15 144227 8705 18255 40292 158 4460 33 27686 16 6 142325 6 3 138 3912 6 66000 138 66000 3912 66000 6 66000 66000 138 66000 66000 3912 66000 66000 80308 1031 5 363 138 27 363 6 149561 78270 48967 201344 705 23638 213 9007 133 1879 2681 2592 135224 1906 6087 6 110405 1369 69112 69112 69112 14271 29 117152 5106 4765 4765 1135 164721 164721 164721 58 58 58 58 2551 90827 32 85908 87 25 272 2809 242 18 18345 764 25 7 2685 4 242 11766 398 9077 32 242 594 959 9077 87 25 1181 3249 442 4 242 397 398 1884 3060 26156 32 1401 25 26455 10 25 141 866
1 change: 1 addition & 0 deletions tests/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,7 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${CMAKE
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-bpe ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-spm ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-spm.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-mpt ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-nomic-bert-moe ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-nomic-bert-moe.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-phi-3 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-phi-3.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-qwen2.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
Expand Down
Loading