Skip to content

Commit

Permalink
models : add phi-3, mpt, gpt-2, starcoder
Browse files Browse the repository at this point in the history
  • Loading branch information
ggerganov committed Apr 29, 2024
1 parent c21ab18 commit 120cf37
Show file tree
Hide file tree
Showing 20 changed files with 645 additions and 10 deletions.
3 changes: 3 additions & 0 deletions Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -64,10 +64,13 @@ test: $(TEST_TARGETS)
if [ "$$test_target" = "tests/test-tokenizer-0" ]; then \
./$$test_target $(CURDIR)/models/ggml-vocab-llama-spm.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-llama-bpe.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-phi-3.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-falcon.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-deepseek-coder.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-deepseek-llm.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-bert-bge.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-starcoder.gguf; \
./$$test_target $(CURDIR)/models/ggml-vocab-gpt-2.gguf; \
elif [ "$$test_target" = "tests/test-tokenizer-1-spm" ]; then \
continue; \
elif [ "$$test_target" = "tests/test-tokenizer-1-bpe" ]; then \
Expand Down
16 changes: 10 additions & 6 deletions convert-hf-to-gguf-update.py
Original file line number Diff line number Diff line change
Expand Up @@ -46,12 +46,16 @@ class TOKENIZER_TYPE(IntEnum):

# TODO: add models here, base models preferred
models = [
{ "name": "llama-spm", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/meta-llama/Llama-2-7b-hf", },
{ "name": "llama-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/meta-llama/Meta-Llama-3-8B", },
{ "name": "deepseek-llm", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-llm-7b-base", },
{ "name": "deepseek-coder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base", },
{ "name": "falcon", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/falcon-7b", },
{ "name": "bert-bge", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/BAAI/bge-small-en-v1.5", },
{ "name": "llama-spm", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/meta-llama/Llama-2-7b-hf", },
{ "name": "llama-bpe", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/meta-llama/Meta-Llama-3-8B", },
{ "name": "phi-3", "tokt": TOKENIZER_TYPE.SPM, "repo": "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct", },
{ "name": "deepseek-llm", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-llm-7b-base", },
{ "name": "deepseek-coder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base", },
{ "name": "falcon", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/falcon-7b", },
{ "name": "bert-bge", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/BAAI/bge-small-en-v1.5", },
{ "name": "mpt", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mosaicml/mpt-7b", },
{ "name": "starcoder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigcode/starcoder2-3b", },
{ "name": "gpt-2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/openai-community/gpt2", },
]

# make directory "models/tokenizers" if it doesn't exist
Expand Down
9 changes: 9 additions & 0 deletions convert-hf-to-gguf.py
Original file line number Diff line number Diff line change
Expand Up @@ -296,6 +296,15 @@ def get_vocab_base_pre(self, tokenizer) -> str:
if chkhsh == "0876d13b50744004aa9aeae05e7b0647eac9d801b5ba4668afc01e709c15e19f":
# ref: https://huggingface.co/BAAI/bge-small-en-v1.5
res = "bert-bge"
if chkhsh == "b6dc8df998e1cfbdc4eac8243701a65afe638679230920b50d6f17d81c098166":
# ref: https://huggingface.co/mosaicml/mpt-7b
res = "mpt"
if chkhsh == "35d91631860c815f952d711435f48d356ebac988362536bed955d43bfa436e34":
# ref: https://huggingface.co/bigcode/starcoder2-3b
res = "starcoder"
if chkhsh == "3ce83efda5659b07b1ad37ca97ca5797ea4285d9b9ab0dc679e4a720c9da7454":
# ref: https://huggingface.co/openai-community/gpt2
res = "gpt-2"

if res is None:
print("\n")
Expand Down
26 changes: 26 additions & 0 deletions llama.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -4352,6 +4352,15 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "falcon") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_FALCON;
} else if (
tokenizer_pre == "mpt") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_MPT;
} else if (
tokenizer_pre == "starcoder") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_STARCODER;
} else if (
tokenizer_pre == "gpt-2") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_GPT2;
} else {
throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
}
Expand Down Expand Up @@ -12124,6 +12133,23 @@ struct llm_tokenizer_bpe {
"[0-9][0-9][0-9]",
});
break;
case LLAMA_VOCAB_PRE_TYPE_MPT:
// TODO: MPT pre-tokenization regexes are unknown
// the following are close, but not exact. run the following:
// ./bin/test-tokenizer-0 ../models/ggml-vocab-mpt.gguf
GGML_ASSERT("MPT pre-tokenization regexes are unknown - fixes needed");
word_collection = unicode_regex_split(text, {
"\\s?\\p{L}+",
"\\s?\\p{P}+",
"'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
});
break;
case LLAMA_VOCAB_PRE_TYPE_STARCODER:
case LLAMA_VOCAB_PRE_TYPE_GPT2:
word_collection = unicode_regex_split(text, {
"'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)",
});
break;
default:
// default regex for BPE tokenization pre-processing
word_collection = unicode_regex_split(text, {
Expand Down
3 changes: 3 additions & 0 deletions llama.h
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,9 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_DEEPSEEK_LLM = 2,
LLAMA_VOCAB_PRE_TYPE_DEEPSEEK_CODER = 3,
LLAMA_VOCAB_PRE_TYPE_FALCON = 4,
LLAMA_VOCAB_PRE_TYPE_MPT = 5,
LLAMA_VOCAB_PRE_TYPE_STARCODER = 6,
LLAMA_VOCAB_PRE_TYPE_GPT2 = 7,
};

// note: these values should be synchronized with ggml_rope
Expand Down
Binary file added models/ggml-vocab-gpt-2.gguf
Binary file not shown.
102 changes: 102 additions & 0 deletions models/ggml-vocab-gpt-2.gguf.inp
Original file line number Diff line number Diff line change
@@ -0,0 +1,102 @@

__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__
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__











🚀 (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__
41 changes: 41 additions & 0 deletions models/ggml-vocab-gpt-2.gguf.out
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@

220
220 220
220 220 220
197
198
628
628 198
197 198
15496 995
18435 995
15496 2159
18435 2159
18435 2159 0
15496 11 995 0
18435 11 995 0
428 318 12520 99 247 13 20322
86 47202 767 28047 45961 288 82 7568 13415
22177 16843 141 231 15166 12466 121 16142 12466 239 141 232 30143 140 111 16142 21169 21727 31583 18849
157 252 222 157 252 114 157 252 241 157 253 233 157 252 237 157 253 224 157 252 244 157 252 115 157 252 253 157 253 223 157 252 253 157 252 95 157 252 114 157 252 227 157 252 223 157 252 249 157 252 227 157 253 223 157 252 231
8582 248 222 357 11265 8 30325 114 447 235 8582 234 104 37929 357 48101 795 13210 271 1673 36686 515 8 14519 227 357 8807 44805 326 468 663 898 11241 8
15496
18435
220 18435
220 220 18435
220 220 220 18435
220 220 220 18435 198 220 220 220 18435
357
198 796
6 6980
15496 11 331 6 439 0 1374 389 345 30325 223 5633 22755 239 46349 111 28839 101 18040 32432 98 43291 1485 1415 24309 25465 171 121 252
18
2091
20370
24840
2091 20370
24840 2091
24840 20370
24840 24840
24840 2091 20370
198 220 628 220 628 198 220 197 220 197 197 220 197 198 220 220 198 220 220 220 198 220 220 220 220 198 220 220 220 220 220 198 8582 248 222 357 11265 8 30325 114 447 235 8582 234 104 37929 357 48101 795 13210 271 1673 36686 515 8 14519 227 12520 99 247 8582 99 247 513 4747 23460 513 20370 23460 2091 23460 20370 23460 24840 23460 2091 20370 513 13 18 513 492 18 513 986 18 28053 252 222 157 252 114 157 252 241 157 253 233 157 252 237 157 253 224 157 252 244 157 252 115 157 252 253 157 253 223 157 252 253 157 252 95 157 252 114 157 252 227 47249 223 5633 22755 239 46349 111 28839 101 18040 32432 98 43291 1485 1415 24309 25465 171 121 252 40103 1421 18604 12466 121 16843 141 231 15166 12466 121 16142 12466 239 141 232 30143 140 111 16142 21169 21727 31583 18849 705 39115 6 33153 15506 63 15931 15931 16317 13896 3228 9805 3548 314 1053 587 705 44040 339 338 612 11 705 2200 345 1654 30 705 44 407 1654 314 1183 787 340 11 705 35 345 588 617 8887 30 775 6 26979 257 6 75 43
Binary file modified models/ggml-vocab-mpt.gguf
Binary file not shown.
102 changes: 102 additions & 0 deletions models/ggml-vocab-mpt.gguf.inp
Original file line number Diff line number Diff line change
@@ -0,0 +1,102 @@

__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__
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__











🚀 (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__
41 changes: 41 additions & 0 deletions models/ggml-vocab-mpt.gguf.out
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@

209
50276
50275
186
187
535
2756
186 187
12092 1533
24387 1533
12092 3645
24387 3645
24387 3645 2
12092 13 1533 2
24387 13 1533 2
436 310 22692 101 236 15 14161
88 27244 818 16853 16392 20505 4989 11917
32520 11514 1068 8713 38177 13396 3415 9925 12559 10453 1389
18081 211 18081 116 18081 230 39936 222 18081 226 39936 213 18081 233 18081 117 18081 242 39936 212 18081 242 18081 97 18081 116 18081 216 18081 212 18081 238 18081 216 39936 212 18081 220
14931 237 211 313 6320 10 49042 116 325 224 14931 223 106 171 118 226 313 34263 802 13511 261 32147 456 10 3384 239 216 313 7483 802 80 8020 326 556 697 1211 10669 10
12092
24387
50276 12092
50275 12092
50274 12092
50274 12092 187 50274 12092
313
187 426
8 8685
12092 13 340 8 455 2 1359 403 368 49042 212 3736 15367 41197 13610 19934 41869 21275 1012 1047 18795 40120 20422 241
20
1610
20084
26409
1610 20084
26409 1610
26409 20084
26409 26409
26409 1610 20084
586 1744 33525 186 209 623 28910 187 50276 187 50275 187 50274 187 50273 187 14931 237 211 313 6320 10 49042 116 325 224 14931 223 106 171 118 226 313 34263 802 13511 261 32147 456 10 3384 239 216 22692 101 236 14931 101 236 495 5922 30057 495 20084 495 26409 30057 20084 495 26409 1610 495 26409 20084 495 15 20 495 537 20 495 1051 20 209 18081 211 18081 116 18081 230 39936 222 18081 226 39936 213 18081 233 18081 117 18081 242 39936 212 18081 242 18081 97 18081 116 18081 216 14931 235 212 3736 15367 41197 13610 19934 41869 21275 1012 1047 18795 40120 20422 241 16081 6877 12880 11514 1068 8713 38177 13396 3415 9925 12559 10453 1389 42011 35033 34842 11202 9739 9739 33021 18963 4672 25561 8220 309 1849 644 686 42618 344 434 627 13 686 1848 368 2119 32 686 46 417 2119 309 1833 1056 352 13 686 37 368 751 690 10331 32 844 8 31516 247 8 77 45
Binary file added models/ggml-vocab-phi-3.gguf
Binary file not shown.
Loading

0 comments on commit 120cf37

Please sign in to comment.