vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

tests : add test-tokenizer-0.sh + fix some tokenizers (#7036)

Browse source 
* tests : add test-tokenizer-0.sh

* unicode : add all unicode number ranges

* starcoder : fix pre-tokenizer

* tests : add test that fails with DeepSeek tokenizers

* falcon : fix regex

* unicode : regenerate unicode tables

* refact : add tokenizer model

* lint : fix

* tests : disable failing tests

ggml-ci

* refact : add tests files

ggml-ci

* convert : print -> logging

ggml-ci

* lint : fix

* unicode : digit -> number

* phi-3 : update
This commit is contained in:
Georgi Gerganov 2024-05-04 08:32:32 +03:00 • committed by GitHub
parent a2ac89d6ef
commit 92139b90af
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
41 changed files with 903 additions and 719 deletions
Download patch file Download diff file Expand all files Collapse all files

46
tests/test-tokenizer-0.py Normal file
View file

@ -0,0 +1,46 @@
import time
import argparse
from transformers import AutoTokenizer
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", required=True)
args = parser.parse_args()
dir_tokenizer = args.dir_tokenizer
fname_tok = args.fname_tok
tokenizer = AutoTokenizer.from_pretrained(dir_tokenizer)
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)
t_start = time.time()
res = tokenizer.encode(s, add_special_tokens=False)
t_end = time.time()
print('\nmain : tokenized in', "{:.3f}".format(1000.0 * (t_end - t_start)), 'ms (py)')
with open(fname_out, 'w', encoding='utf-8') as f:
for x in res:
# LLaMA v3 for some reason strips the space for these tokens (and others)
# if x == 662:
# f.write(str(x) + ' \' ' + tokenizer.decode(x) + '\'\n')
# elif x == 1174:
# f.write(str(x) + ' \' ' + tokenizer.decode(x) + '\'\n')
# elif x == 2564:
# f.write(str(x) + ' \' ' + tokenizer.decode(x) + '\'\n')
# elif x == 758:
# f.write(str(x) + ' \' ' + tokenizer.decode(x) + '\'\n')
# elif x == 949:
# f.write(str(x) + ' \' ' + tokenizer.decode(x) + '\'\n')
# elif x == 5354:
# f.write(str(x) + ' \' ' + tokenizer.decode(x) + '\'\n')
# else:
# f.write(str(x) + ' \'' + tokenizer.decode(x) + '\'\n')
# f.write(str(x) + ' \'' + tokenizer.decode(x).strip() + '\'\n')
f.write(str(x) + '\n')
print('len(res): ', len(res))
print('len(lines): ', len(lines))
print('results written to: ', fname_out)