Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix CircleCI failures on Windows for XLM-R unit tests #1441

Merged
merged 1 commit into from
Nov 12, 2021
Merged

Fix CircleCI failures on Windows for XLM-R unit tests #1441

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion torchtext/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
import os
_TEXT_BUCKET = 'https://download.pytorch.org/models/text'
_TEXT_BUCKET = 'https://download.pytorch.org/models/text/'
_CACHE_DIR = os.path.expanduser('~/.torchtext/cache')

from . import data
Expand Down
14 changes: 7 additions & 7 deletions torchtext/models/roberta/bundler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@

import os
from dataclasses import dataclass
from functools import partial
from urllib.parse import urljoin

from typing import Optional, Callable
from torchtext._download_hooks import load_state_dict_from_url
Expand Down Expand Up @@ -100,19 +100,19 @@ def encoderConf(self) -> RobertaEncoderConf:


XLMR_BASE_ENCODER = RobertaModelBundle(
_path=os.path.join(_TEXT_BUCKET, "xlmr.base.encoder.pt"),
_path=urljoin(_TEXT_BUCKET, "xlmr.base.encoder.pt"),
_encoder_conf=RobertaEncoderConf(vocab_size=250002),
transform=partial(get_xlmr_transform,
vocab_path=os.path.join(_TEXT_BUCKET, "xlmr.vocab.pt"),
spm_model_path=os.path.join(_TEXT_BUCKET, "xlmr.sentencepiece.bpe.model"),
vocab_path=urljoin(_TEXT_BUCKET, "xlmr.vocab.pt"),
spm_model_path=urljoin(_TEXT_BUCKET, "xlmr.sentencepiece.bpe.model"),
)
)

XLMR_LARGE_ENCODER = RobertaModelBundle(
_path=os.path.join(_TEXT_BUCKET, "xlmr.large.encoder.pt"),
_path=urljoin(_TEXT_BUCKET, "xlmr.large.encoder.pt"),
_encoder_conf=RobertaEncoderConf(vocab_size=250002, embedding_dim=1024, ffn_dimension=4096, num_attention_heads=16, num_encoder_layers=24),
transform=partial(get_xlmr_transform,
vocab_path=os.path.join(_TEXT_BUCKET, "xlmr.vocab.pt"),
spm_model_path=os.path.join(_TEXT_BUCKET, "xlmr.sentencepiece.bpe.model"),
vocab_path=urljoin(_TEXT_BUCKET, "xlmr.vocab.pt"),
spm_model_path=urljoin(_TEXT_BUCKET, "xlmr.sentencepiece.bpe.model"),
)
)