huggingface / transformers

Watch 582
Star 27.4k
Fork 6.5k

Code
Issues 456
Pull requests 88
Actions
Projects 0
Security
Insights

Code Issues 456 Pull requests 88 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.

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

456 Open 2,547 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

Tokenize something with a "." in between Decode these ids, you will find it mismatch

#4497 opened May 21, 2020 by Xunzhuo

python run_glue.py with the AttributeError: 'NoneType' object has no attribute 'seek'

#4496 opened May 21, 2020 by zhuqunxi

❓ [BART] Why Decoder Layer Normalization is applied only at the last layer ?

#4495 opened May 21, 2020 by Colanim

Incorporate HuggingFace 'nlp' library in examples

#4494 opened May 21, 2020 by nateraw

Cannot load reformer-enwik8 tokenizer

#4492 opened May 20, 2020 by erickrf

Can't find vocabulary file or is corrupted for MarianTokenizer

#4491 opened May 20, 2020 by pgfeldman 0 of 2

How to load a pruned Albert model with from_pretrained()?

#4490 opened May 20, 2020 by ThomasSYT

tokenizer.vocab has not changed after using add_tokens

#4486 opened May 20, 2020 by suyulan

Can't find vocabulary file or is corrupted for MarianTokenizer

#4485 opened May 20, 2020 by sadeqa

Bug using Roberta models in QA Transformers pipeline.

#4484 opened May 20, 2020 by thiagomoeng

Trying to add support for GPT2 as decoder in EncoderDecoder model

#4483 opened May 20, 2020 by dimi1357

❓ [TPU] [Trainer] Moving model to device before setting optimizer slow the training

#4478 opened May 20, 2020 by Colanim

Tokenizer encode to have an option to overflow from left

#4476 opened May 20, 2020 by misrasaurabh1

Request for hosting model files in a Virtual Hosted-Style S3 buckets

#4475 opened May 20, 2020 by rjsaito

batch_encode_plus returns same lengths when enable pad_to_max_length

#4471 opened May 19, 2020 by binh-vu 1 of 4

ProjectedAdaptiveLogSoftmax.log_prob raises Exception

#4461 opened May 19, 2020 by klicperajo 2 of 4

Pretrained Transformer-XL gives unreasonable result on WikiText-103

#4459 opened May 19, 2020 by klicperajo 2 of 4

FastTokenizer add_special_tokens also adding individual characters for multi character tokens

#4457 opened May 19, 2020 by jwallat 2 of 2

get output from a particular layer of pre-trained transformer (xlnet)

#4455 opened May 19, 2020 by mainulquraishi

DMOZ - web page classification / multi-language

#4454 opened May 19, 2020 by x0rzkov

Bug - TFBertForSequenceClassification on SQUaD data

#4453 opened May 19, 2020 by yonatanbitton 0 of 2

[Questions & Help] The loss doesn't decrease correctly while training BERT from scratch

#4449 opened May 19, 2020 by ghrua

TF Beam Search generation seems to be flaky sometimes

#4447 opened May 18, 2020 by patrickvonplaten 0 of 5

Generation with EncoderDecoder Model

#4445 opened May 18, 2020 by manzar96

model.save() does not save keras model that includes DIstillBert layer

#4444 opened May 18, 2020 by msahamed

Previous 1 2 3 4 5 … 18 19 Next

Previous Next

ProTip! no:milestone will show everything without a milestone.

Apr	MAY	Jun
	21
2019	2020	2021