f23c0359a3
Disabled rules:
* E203 Whitespace before ':' - disabled because we often use 'C' Style where values are aligned
* E211 Whitespace before '(' (E211) - disabled because we often use 'C' Style where values are aligned
* E221 Multiple spaces before operator - disabled because we often use 'C' Style where values are aligned
* E225 Missing whitespace around operator - disabled because it's broken so often it seems like a standard
* E231 Missing whitespace after ',', ';', or ':' - disabled because we often use 'C' Style where values are aligned
* E241 Multiple spaces after ',' - disabled because we often use 'C' Style where values are aligned
* E251 Unexpected spaces around keyword / parameter equals - disabled because it's broken so often it seems like a standard
* E261 At least two spaces before inline comment - disabled because it's broken so often it seems like a standard
* E266 Too many leading '#' for block comment - sometimes used as "section" separator
* E501 Line too long - disabled because it's broken so often it seems like a standard
* E701 Multiple statements on one line (colon) - broken only in convert.py when defining abstract methods (we can use# noqa instead)
* E704 Multiple statements on one line - broken only in convert.py when defining abstract methods (we can use# noqa instead)
83 lines
2.1 KiB
Python
83 lines
2.1 KiB
Python
# tests with BPE tokenizer
|
|
|
|
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")
|
|
args = parser.parse_args()
|
|
|
|
dir_tokenizer = args.dir_tokenizer
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(dir_tokenizer)
|
|
|
|
tests = [
|
|
"",
|
|
" ",
|
|
" ",
|
|
" ",
|
|
"\t",
|
|
"\n",
|
|
"\t\n",
|
|
"Hello world",
|
|
" Hello world",
|
|
"Hello World",
|
|
" Hello World",
|
|
" Hello World!",
|
|
"Hello, world!",
|
|
" Hello, world!",
|
|
" this is 🦙.cpp",
|
|
"w048 7tuijk dsdfhu",
|
|
"нещо на Български",
|
|
"កាន់តែពិសេសអាចខលចេញ",
|
|
"🚀 (normal) 😶🌫️ (multiple emojis concatenated) ✅ (only emoji that has its own token)",
|
|
"Hello",
|
|
" Hello",
|
|
" Hello",
|
|
" Hello",
|
|
" Hello",
|
|
" Hello\n Hello",
|
|
"\n =",
|
|
"' era",
|
|
]
|
|
|
|
for text in tests:
|
|
print('text: ', text)
|
|
print(tokenizer.encode(text))
|
|
print(tokenizer.decode(tokenizer.encode(text)))
|
|
|
|
print("\n\ntests for C++:\n")
|
|
for text in tests:
|
|
res = tokenizer.encode(text)
|
|
|
|
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)
|
|
# 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)
|