pytorch / fairseq

Watch 264
Star 8.1k
Fork 2k

Code
Issues 246
Pull requests 41
Actions
Projects 0
Security
Insights

Code Issues 246 Pull requests 41 Projects 0 Actions Security Pulse

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.

Pick a username

Email Address

Password

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

246 Open 1,324 Closed

Author

Filter by author

Label

Filter by label

Use alt + click/return to exclude labels.

Projects

Filter by project

Milestones

Filter by milestone

Assignee

Filter by who’s assigned

Sort

Sort by

Newest Oldest Most commented Least commented Recently updated Least recently updated

Most reactions

[QuantNoise] QuantNoise convertion for custom / own model outside of fairseq? needs triage question

#2236 opened Jun 11, 2020 by Oskop

gelu_accurate: nan gradient with fp16. add an inner cast to float32? bug needs triage

#2235 opened Jun 11, 2020 by vadimkantorov

"--print-alignment" argument drastically slows down the generation bug needs triage

#2234 opened Jun 11, 2020 by ladler0320

Help with using Pointer-Generator for abstractive summarization needs triage question

#2233 opened Jun 10, 2020 by griff4692

Problem with training transformer translation model with quant-noise-pq needs triage question

#2232 opened Jun 9, 2020 by jahutwb

[BUG] AssertionError: sentence at index 0 of size 3514 exceeds max_tokens limit of 2000! in fairseq/fairseq/trainer.py bug needs triage

#2231 opened Jun 9, 2020 by 107368511

checkpoint saving skipped at the end of an epoch bug needs triage

#2230 opened Jun 9, 2020 by jesgim

Number of types in dictionary - log needs triage question

#2227 opened Jun 9, 2020 by gvskalyan

'fairseq-train' does not appear to train question

#2224 opened Jun 8, 2020 by JustCunn

mBART: Fine-tuning on an unseen language needs triage question

#2223 opened Jun 8, 2020 by ddaspit

[BUG] AttributeError: 'float' object has no attribute 'itemsize' in indexed_dataset.py

#2221 opened Jun 8, 2020 by memeda

BART Abstractive Summarization : What is the maximum number of input tokens ? needs triage question

#2220 opened Jun 7, 2020 by shamanez

Extract embedding from NMT, apply some transformation, use it back to finetune needs triage question

#2219 opened Jun 7, 2020 by nishaahmed

Size Mismatch error when training translation_from_pretrained_xlm needs triage question

#2218 opened Jun 7, 2020 by ajesujoba

hello,how to fine tune question-answering dataset(such as SQuad1.0 or SQuad2.0) using bart-large model?thank you ver much! needs triage question

#2217 opened Jun 7, 2020 by ChengchengDu

ZeroDivisionError: division by zero question

#2216 opened Jun 6, 2020 by samin9796

ImportError: cannot import name 'rerank' documentation

#2213 opened Jun 5, 2020 by Bachstelze

[Translation MOE] Different Model Performance with Paper question

#2212 opened Jun 5, 2020 by juheeuu

generate for Glue score JFLEG data fails needs triage question

#2211 opened Jun 4, 2020 by NikhilCherian

Visualizing attn maps needs triage question

#2210 opened Jun 4, 2020 by AhmedTElthakeb

Is the first target token ignored? (`translation` task w/ `bart.base` arch) needs triage question

#2209 opened Jun 4, 2020 by pltrdy

Improving levt transformer training speed enhancement help wanted needs triage

#2208 opened Jun 4, 2020 by mingruimingrui

quant_noise.py, process for kernel_size==(1,1) change input weight size ,cause error bug needs triage

#2207 opened Jun 4, 2020 by misslibra

Possibly wrong link of roberta base model with layerdrop ？ documentation needs triage

#2206 opened Jun 4, 2020 by zhuango

ReduceLROnPlateau does not support `maximize-best-checkpoint-metric` bug

#2205 opened Jun 2, 2020 by pietruh

Previous 1 2 3 4 5 … 9 10 Next

Previous Next

ProTip! Follow long discussions with comments:>50.