# Code from https://github.com/openai/CLIP
import gzip
import html
import os
from functools import lru_cache
import hashlib
import urllib
from tqdm import tqdm
import regex as re
CLIP_VOCAB = "https://github.com/backprop-ai/backprop/raw/main/backprop/models/clip/bpe_simple_vocab_16e6.txt.gz"
[docs]@lru_cache()
def default_bpe():
return _download_vocab()
[docs]@lru_cache()
def bytes_to_unicode():
"""
Returns list of utf-8 byte and a corresponding list of unicode strings.
The reversible bpe codes work on unicode strings.
This means you need a large # of unicode characters in your vocab if you want to avoid UNKs.
When you're at something like a 10B token dataset you end up needing around 5K for decent coverage.
This is a signficant percentage of your normal, say, 32K bpe vocab.
To avoid that, we want lookup tables between utf-8 bytes and unicode strings.
And avoids mapping to whitespace/control characters the bpe code barfs on.
"""
bs = list(range(ord("!"), ord("~")+1))+list(range(ord("¡"), ord("¬")+1))+list(range(ord("®"), ord("ÿ")+1))
cs = bs[:]
n = 0
for b in range(2**8):
if b not in bs:
bs.append(b)
cs.append(2**8+n)
n += 1
cs = [chr(n) for n in cs]
return dict(zip(bs, cs))
[docs]def get_pairs(word):
"""Return set of symbol pairs in a word.
Word is represented as tuple of symbols (symbols being variable-length strings).
"""
pairs = set()
prev_char = word[0]
for char in word[1:]:
pairs.add((prev_char, char))
prev_char = char
return pairs
[docs]def basic_clean(text):
import ftfy
text = ftfy.fix_text(text)
text = html.unescape(html.unescape(text))
return text.strip()
[docs]def whitespace_clean(text):
text = re.sub(r'\s+', ' ', text)
text = text.strip()
return text
def _download_vocab(url: str = CLIP_VOCAB, root: str = os.path.expanduser("~/.cache/backprop/clip")):
os.makedirs(root, exist_ok=True)
filename = os.path.basename(url)
download_target = os.path.join(root, filename)
if os.path.exists(download_target) and not os.path.isfile(download_target):
raise RuntimeError(f"{download_target} exists and is not a regular file")
if os.path.isfile(download_target):
if hashlib.sha256(open(download_target, "rb").read()).hexdigest():
return download_target
with urllib.request.urlopen(url) as source, open(download_target, "wb") as output:
with tqdm(total=int(source.info().get("Content-Length")), ncols=80) as loop:
while True:
buffer = source.read(8192)
if not buffer:
break
output.write(buffer)
loop.update(len(buffer))
return download_target
[docs]class SimpleTokenizer(object):
def __init__(self):
bpe_path = _download_vocab()
self.byte_encoder = bytes_to_unicode()
self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
merges = gzip.open(bpe_path).read().decode("utf-8").split('\n')
merges = merges[1:49152-256-2+1]
merges = [tuple(merge.split()) for merge in merges]
vocab = list(bytes_to_unicode().values())
vocab = vocab + [v+'</w>' for v in vocab]
for merge in merges:
vocab.append(''.join(merge))
vocab.extend(['<|startoftext|>', '<|endoftext|>'])
self.encoder = dict(zip(vocab, range(len(vocab))))
self.decoder = {v: k for k, v in self.encoder.items()}
self.bpe_ranks = dict(zip(merges, range(len(merges))))
self.cache = {'<|startoftext|>': '<|startoftext|>', '<|endoftext|>': '<|endoftext|>'}
self.pat = re.compile(r"""<\|startoftext\|>|<\|endoftext\|>|'s|'t|'re|'ve|'m|'ll|'d|[\p{L}]+|[\p{N}]|[^\s\p{L}\p{N}]+""", re.IGNORECASE)
[docs] def bpe(self, token):
if token in self.cache:
return self.cache[token]
word = tuple(token[:-1]) + ( token[-1] + '</w>',)
pairs = get_pairs(word)
if not pairs:
return token+'</w>'
while True:
bigram = min(pairs, key = lambda pair: self.bpe_ranks.get(pair, float('inf')))
if bigram not in self.bpe_ranks:
break
first, second = bigram
new_word = []
i = 0
while i < len(word):
try:
j = word.index(first, i)
new_word.extend(word[i:j])
i = j
except:
new_word.extend(word[i:])
break
if word[i] == first and i < len(word)-1 and word[i+1] == second:
new_word.append(first+second)
i += 2
else:
new_word.append(word[i])
i += 1
new_word = tuple(new_word)
word = new_word
if len(word) == 1:
break
else:
pairs = get_pairs(word)
word = ' '.join(word)
self.cache[token] = word
return word
[docs] def encode(self, text):
bpe_tokens = []
text = whitespace_clean(basic_clean(text)).lower()
for token in re.findall(self.pat, text):
token = ''.join(self.byte_encoder[b] for b in token.encode('utf-8'))
bpe_tokens.extend(self.encoder[bpe_token] for bpe_token in self.bpe(token).split(' '))
return bpe_tokens
[docs] def decode(self, tokens):
text = ''.join([self.decoder[token] for token in tokens])
text = bytearray([self.byte_decoder[c] for c in text]).decode('utf-8', errors="replace").replace('</w>', ' ')
return text