ConnorJL GPT2 issues - Githubissues

ConnorJL / GPT2

An implementation of training for GPT2, supports TPUs

MIT License

1.42k stars 338 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Question about the metric reported in the paper?

#38 dsj96 opened 1 year ago
0
CVE-2007-4559 Patch

#37 TrellixVulnTeam opened 1 year ago
0
create_tfrecords.py。Dealing with problems with your own data set

#36 xsyzka closed 2 years ago
0
where is the length of the forecast article set? Thank you!

#35 xsyzka opened 2 years ago
0
Samples?

#34 sleepinyourhat opened 3 years ago
0
Training 1.5B?

#33 JulesGM opened 3 years ago
0
Retraining a new model, only gpu 0 can be used

#32 yds1024 closed 3 years ago
1
Error on output

#31 silicahd opened 3 years ago
1
GPT vs BERT, under same computation and data resource, which one is better for downstream tasks like GLUE?

#30 guotong1988 opened 3 years ago
0
117M/model.ckpt.index is corrupted?

#29 ksjae opened 3 years ago
0
character-level

#28 amacfie closed 3 years ago
1
about encoder.json

#27 fnyhy opened 4 years ago
4
DOCKER: Web interface doesn't work

#26 fartwhif opened 4 years ago
0
Docker documentation for CUDA

#25 fartwhif opened 4 years ago
0
Training on artificial language data (server logs, medical records, etc.)

#24 klimentij closed 4 years ago
1
I figured out how to cram GPT-2 1.5B onto a single TPU core with Adam optimizer

#23 shawwn opened 4 years ago
3
How can i create smaller sized file for inference of 1.5B model

#22 pragnakalpdev6 closed 4 years ago
1
Are there some research papers about text-to-set generation?

#21 guotong1988 closed 4 years ago
1
error when using create_tfrecords.py

#20 CrackerHax closed 4 years ago
3
Your 1.5B model

#19 4R7I5T closed 4 years ago
2
when reading metadata of gs://openwebtext/stuff/encoder/encoder.json

#18 makamkkumar closed 4 years ago
1
Update create_tfrecords.py

#17 cedspam opened 4 years ago
2
Downloading Encoder Model fails

#16 PickHub closed 4 years ago
2
Training problem

#15 DrYangLiu opened 4 years ago
1
Why gpt-2 could apply to other tasks without fine-tune?

#14 guotong1988 closed 4 years ago
2
format dataset

#13 khaerulumam42 opened 5 years ago
6
what's the difference between sample and sample_free?

#12 Tianyu00 closed 5 years ago
1
quirks that hold the model back

#11 murpen opened 5 years ago
4
To train my model means fit-tuning or retrain a model?

#10 wjy979769265 opened 5 years ago
4
Fix path to text extraction scripts

#9 vochicong closed 5 years ago
1
!): Fix for tensorflow-gpu == 1.12.0 case.

#8 tbfly closed 5 years ago
1
chore(readme): fix typo

#7 hong4rc closed 5 years ago
1
Has anyone managed to work it on Windows? Which OS did you use to make it work?

#6 FurkanGozukara opened 5 years ago
2
Input Chinese, the predicted is Japanese.

#5 dpyneo opened 5 years ago
9
Predicting with PrettyBigModel `InvalidArgumentError: indices[0,0] = 1024 is not in [0, 1024)`

#4 pkmital closed 5 years ago
5
A meaningful performance comparison with OpenAI's models

#3 lostmsu closed 5 years ago
5
How to process raw text files to create similar "PrettyBig" model?

#2 GenTxt closed 5 years ago
5
Unable to predict with bfloat16 model

#1 kizinfo closed 5 years ago
2