Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / ConnorJL/GPT2 issues and pull requests
#38 - Question about the metric reported in the paper?
Issue -
State: open - Opened by dsj96 over 1 year ago
#37 - CVE-2007-4559 Patch
Pull Request -
State: open - Opened by TrellixVulnTeam almost 2 years ago
#36 - create_tfrecords.py。Dealing with problems with your own data set
Issue -
State: closed - Opened by xsyzka over 2 years ago
#35 - where is the length of the forecast article set? Thank you!
Issue -
State: open - Opened by xsyzka over 2 years ago
#34 - Samples?
Issue -
State: open - Opened by sleepinyourhat almost 4 years ago
#33 - Training 1.5B?
Issue -
State: open - Opened by JulesGM about 4 years ago
#32 - Retraining a new model, only gpu 0 can be used
Issue -
State: closed - Opened by yds1024 about 4 years ago
- 1 comment
#31 - Error on output
Issue -
State: open - Opened by silicahd about 4 years ago
- 1 comment
#30 - GPT vs BERT, under same computation and data resource, which one is better for downstream tasks like GLUE?
Issue -
State: open - Opened by guotong1988 about 4 years ago
#29 - 117M/model.ckpt.index is corrupted?
Issue -
State: open - Opened by ksjae about 4 years ago
#28 - character-level
Issue -
State: closed - Opened by amacfie over 4 years ago
- 1 comment
#27 - about encoder.json
Issue -
State: open - Opened by fnyhy almost 5 years ago
- 4 comments
#26 - DOCKER: Web interface doesn't work
Issue -
State: open - Opened by fartwhif almost 5 years ago
#25 - Docker documentation for CUDA
Issue -
State: open - Opened by fartwhif almost 5 years ago
#24 - Training on artificial language data (server logs, medical records, etc.)
Issue -
State: closed - Opened by klimentij almost 5 years ago
- 1 comment
#23 - I figured out how to cram GPT-2 1.5B onto a single TPU core with Adam optimizer
Issue -
State: open - Opened by shawwn almost 5 years ago
- 3 comments
#22 - How can i create smaller sized file for inference of 1.5B model
Issue -
State: closed - Opened by pragnakalpdev6 almost 5 years ago
- 1 comment
#21 - Are there some research papers about text-to-set generation?
Issue -
State: closed - Opened by guotong1988 almost 5 years ago
- 1 comment
#20 - error when using create_tfrecords.py
Issue -
State: closed - Opened by CrackerHax almost 5 years ago
- 3 comments
#19 - Your 1.5B model
Issue -
State: closed - Opened by 4R7I5T about 5 years ago
- 2 comments
#18 - when reading metadata of gs://openwebtext/stuff/encoder/encoder.json
Issue -
State: closed - Opened by makamkkumar about 5 years ago
- 1 comment
#17 - Update create_tfrecords.py
Pull Request -
State: open - Opened by cedspam about 5 years ago
- 2 comments
#16 - Downloading Encoder Model fails
Issue -
State: closed - Opened by PickHub over 5 years ago
- 2 comments
#15 - Training problem
Issue -
State: open - Opened by DrYangLiu over 5 years ago
- 1 comment
#14 - Why gpt-2 could apply to other tasks without fine-tune?
Issue -
State: closed - Opened by guotong1988 over 5 years ago
- 2 comments
#13 - format dataset
Issue -
State: open - Opened by khaerulumam42 over 5 years ago
- 6 comments
#12 - what's the difference between sample and sample_free?
Issue -
State: closed - Opened by Tianyu00 over 5 years ago
- 1 comment
#11 - quirks that hold the model back
Issue -
State: open - Opened by murpen over 5 years ago
- 4 comments
#10 - To train my model means fit-tuning or retrain a model?
Issue -
State: open - Opened by wjy979769265 over 5 years ago
- 4 comments
#9 - Fix path to text extraction scripts
Pull Request -
State: closed - Opened by vochicong over 5 years ago
- 1 comment
#8 - !): Fix for tensorflow-gpu == 1.12.0 case.
Pull Request -
State: closed - Opened by tbfly over 5 years ago
- 1 comment
#7 - chore(readme): fix typo
Pull Request -
State: closed - Opened by hong4rc over 5 years ago
- 1 comment
#6 - Has anyone managed to work it on Windows? Which OS did you use to make it work?
Issue -
State: open - Opened by FurkanGozukara over 5 years ago
- 2 comments
#5 - Input Chinese, the predicted is Japanese.
Issue -
State: open - Opened by dpyneo over 5 years ago
- 9 comments
#4 - Predicting with PrettyBigModel `InvalidArgumentError: indices[0,0] = 1024 is not in [0, 1024)`
Issue -
State: closed - Opened by pkmital over 5 years ago
- 5 comments
#3 - A meaningful performance comparison with OpenAI's models
Issue -
State: closed - Opened by lostmsu over 5 years ago
- 5 comments
#2 - How to process raw text files to create similar "PrettyBig" model?
Issue -
State: closed - Opened by GenTxt over 5 years ago
- 5 comments
#1 - Unable to predict with bfloat16 model
Issue -
State: closed - Opened by kizinfo over 5 years ago
- 2 comments