Spaces:
Runtime error
Runtime error
File size: 2,399 Bytes
58627fa |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
import torch
# from transformers import BertTokenizerFast
from colbert.modeling.hf_colbert import HF_ColBERT
from colbert.infra import ColBERTConfig
from colbert.modeling.tokenization.utils import _split_into_batches, _sort_by_length
class DocTokenizer():
def __init__(self, config: ColBERTConfig):
self.tok = HF_ColBERT.raw_tokenizer_from_pretrained(config.checkpoint)
self.config = config
self.doc_maxlen = config.doc_maxlen
self.D_marker_token, self.D_marker_token_id = '[D]', self.tok.convert_tokens_to_ids('[unused1]')
self.cls_token, self.cls_token_id = self.tok.cls_token, self.tok.cls_token_id
self.sep_token, self.sep_token_id = self.tok.sep_token, self.tok.sep_token_id
# assert self.D_marker_token_id == 2
def tokenize(self, batch_text, add_special_tokens=False):
assert type(batch_text) in [list, tuple], (type(batch_text))
tokens = [self.tok.tokenize(x, add_special_tokens=False) for x in batch_text]
if not add_special_tokens:
return tokens
prefix, suffix = [self.cls_token, self.D_marker_token], [self.sep_token]
tokens = [prefix + lst + suffix for lst in tokens]
return tokens
def encode(self, batch_text, add_special_tokens=False):
assert type(batch_text) in [list, tuple], (type(batch_text))
ids = self.tok(batch_text, add_special_tokens=False)['input_ids']
if not add_special_tokens:
return ids
prefix, suffix = [self.cls_token_id, self.D_marker_token_id], [self.sep_token_id]
ids = [prefix + lst + suffix for lst in ids]
return ids
def tensorize(self, batch_text, bsize=None):
assert type(batch_text) in [list, tuple], (type(batch_text))
# add placehold for the [D] marker
batch_text = ['. ' + x for x in batch_text]
obj = self.tok(batch_text, padding='longest', truncation='longest_first',
return_tensors='pt', max_length=self.doc_maxlen)
ids, mask = obj['input_ids'], obj['attention_mask']
# postprocess for the [D] marker
ids[:, 1] = self.D_marker_token_id
if bsize:
ids, mask, reverse_indices = _sort_by_length(ids, mask, bsize)
batches = _split_into_batches(ids, mask, bsize)
return batches, reverse_indices
return ids, mask
|