Koboldcpp / tests /test-tokenizer-0-falcon.py
Illumotion's picture
Upload folder using huggingface_hub
f57d7c6
raw
history blame
2.2 kB
# tests with BPE tokenizer
import os
import sys
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 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",
]
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') as f:
lines = f.readlines()
s = ''.join(lines)
res = tokenizer.encode(s)
# write to file
with open(fname_out, 'w') as f:
for x in res:
f.write(str(x) + ' ')
f.write('\n')
print('len(res): ', len(res))
print('len(lines): ', len(lines))
print('results written to: ', fname_out)