From f4ab2a41476600a98067a9474ea8f9e6db41bcfa Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Mon, 29 Apr 2024 16:58:41 +0300 Subject: llama : fix BPE pre-tokenization (#6920) * merged the changes from deepseeker models to main branch * Moved regex patterns to unicode.cpp and updated unicode.h * Moved header files * Resolved issues * added and refactored unicode_regex_split and related functions * Updated/merged the deepseek coder pr * Refactored code * Adding unicode regex mappings * Adding unicode regex function * Added needed functionality, testing remains * Fixed issues * Fixed issue with gpt2 regex custom preprocessor * unicode : fix? unicode_wstring_to_utf8 * lint : fix whitespaces * tests : add tokenizer tests for numbers * unicode : remove redundant headers * tests : remove and rename tokenizer test scripts * tests : add sample usage * gguf-py : reader prints warnings on duplicate keys * llama : towards llama3 tokenization support (wip) * unicode : shot in the dark to fix tests on Windows * unicode : first try custom implementations * convert : add "tokenizer.ggml.pre" GGUF KV (wip) * llama : use new pre-tokenizer type * convert : fix pre-tokenizer type writing * lint : fix * make : add test-tokenizer-0-llama-v3 * wip * models : add llama v3 vocab file * llama : adapt punctuation regex + add llama 3 regex * minor * unicode : set bomb * unicode : set bomb * unicode : always use std::wregex * unicode : support \p{N}, \p{L} and \p{P} natively * unicode : try fix windows * unicode : category support via std::regex * unicode : clean-up * unicode : simplify * convert : add convert-hf-to-gguf-update.py ggml-ci * lint : update * convert : add falcon ggml-ci * unicode : normalize signatures * lint : fix * lint : fix * convert : remove unused functions * convert : add comments * convert : exercise contractions ggml-ci * lint : fix * cmake : refactor test targets * tests : refactor vocab tests ggml-ci * tests : add more vocabs and tests ggml-ci * unicode : cleanup * scripts : ignore new update script in check-requirements.sh * models : add phi-3, mpt, gpt-2, starcoder * tests : disable obsolete ggml-ci * tests : use faster bpe test ggml-ci * llama : more prominent warning for old BPE models * tests : disable test-tokenizer-1-bpe due to slowness ggml-ci --------- Co-authored-by: Jaggzh Co-authored-by: Kazim Abrar Mahi --- tests/test-tokenizer-0-spm.py | 114 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 114 insertions(+) create mode 100644 tests/test-tokenizer-0-spm.py (limited to 'tests/test-tokenizer-0-spm.py') diff --git a/tests/test-tokenizer-0-spm.py b/tests/test-tokenizer-0-spm.py new file mode 100644 index 00000000..be12a6b9 --- /dev/null +++ b/tests/test-tokenizer-0-spm.py @@ -0,0 +1,114 @@ +# tests with SPM tokenizer +# +# sample usage: +# +# python3 tests/test-tokenizer-0-spm.py ~/Data/huggingface/Llama-2-7b-hf/ +# python3 tests/test-tokenizer-0-spm.py ~/Data/huggingface/CodeLlama-34b-Instruct-hf/ +# + + +import argparse + +from sentencepiece import SentencePieceProcessor + +parser = argparse.ArgumentParser() +parser.add_argument("dir_tokenizer", help="directory containing 'tokenizer.model' file") +parser.add_argument("--fname-tok", help="path to a text file to tokenize") +args = parser.parse_args() + +dir_tokenizer = args.dir_tokenizer + +tokenizer = SentencePieceProcessor(dir_tokenizer + '/tokenizer.model') + +tests = [ + "", + " ", + " ", + " ", + "\t", + "\n", + "\n\n", + "\n\n\n", + "\t\n", + "Hello world", + " Hello world", + "Hello World", + " Hello World", + " Hello World!", + "Hello, world!", + " Hello, world!", + " this is πŸ¦™.cpp", + "w048 7tuijk dsdfhu", + "Π½Π΅Ρ‰ΠΎ Π½Π° Π‘ΡŠΠ»Π³Π°Ρ€ΡΠΊΠΈ", + "αž€αžΆαž“αŸ‹αžαŸ‚αž–αž·αžŸαŸαžŸαž’αžΆαž…αžαž›αž…αŸαž‰", + "πŸš€ (normal) πŸ˜Άβ€πŸŒ«οΈ (multiple emojis concatenated) βœ… (only emoji that has its own token)", + "Hello", + " Hello", + " Hello", + " Hello", + " Hello", + " Hello\n Hello", + " (", + "\n =", + "' era", + "Hello, y'all! How are you 😁 ?ζˆ‘ζƒ³εœ¨appleε·₯作1314151倩～", + "3", + "33", + "333", + "3333", + "33333", + "333333", + "3333333", + "33333333", + "333333333", +] + + +for text in tests: + print('text: ', text) + print('\nwith bos:') + print(tokenizer.encode(text, add_bos=True)) + print(tokenizer.decode(tokenizer.encode(text, add_bos=True))) + print('\nwithout bos:') + print(tokenizer.encode(text, add_bos=False)) + print(tokenizer.decode(tokenizer.encode(text, add_bos=False))) + +print("'" + tokenizer.id_to_piece(15043) + "'") # '_Hello' +print("'" + tokenizer.id_to_piece(29871) + "'") # '_' +print("'" + tokenizer.decode([15043]) + "'") # 'Hello' +print("'" + tokenizer.decode([15043, 15043]) + "'") # 'Hello Hello' +print("'" + tokenizer.decode([29871, 15043]) + "'") # ' Hello' +print("'" + tokenizer.decode([29871, 15043, 29871, 15043]) + "'") # ' Hello Hello' + +print("\n\ntests for C++:\n") +for text in tests: + res = tokenizer.encode(text, add_bos=False) + + k = text.replace('\n', '\\n') + k = k.replace('\t', '\\t') + k = '"' + k + '"' + print("{ %-24s, { " % k, end='') + for x in res: + print("%7d," % x, end='') + print(" }, },") + +print(tokenizer.encode('hello')) +print(tokenizer.encode('world')) +print(tokenizer.encode(' world')) +print(tokenizer.encode('hello world')) + +fname_tok = args.fname_tok +if fname_tok: + print('tokenizing file: ', fname_tok) + fname_out = fname_tok + '.tok' + with open(fname_tok, 'r', encoding='utf-8') as f: + lines = f.readlines() + s = ''.join(lines) + res = tokenizer.encode(s, add_bos=True) + # write to file + with open(fname_out, 'w', encoding='utf-8') as f: + for x in res: + f.write(str(x) + ' \'' + tokenizer.decode(x) + '\'\n') + print('len(res): ', len(res)) + print('len(lines): ', len(lines)) + print('results written to: ', fname_out) -- cgit v1.2.3