Skip to content

Issues: ManifoldRG/NEKO

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

39 Open 24 Closed
39 Open 24 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Possible use of padding instead of max tokens to avoid error when calculating loss.
#83 opened Mar 17, 2024 by eihli
The training loss and perplexity is not decreasing for the VQA task
#78 opened Feb 5, 2024 by henryj18
Remove old Neko and Forge branding
#76 opened Feb 1, 2024 by harshsikka
Replace --eval-mode = ['deterministic', 'stochastic'] with temperature.
#74 opened Jan 21, 2024 by eihli
1
Add debug logging?
#73 opened Jan 21, 2024 by eihli
4
Error running eval.py on checkpoint created using --pretrained_lm=gpt2. bug Something isn't working
#71 opened Jan 14, 2024 by eihli
@eihli
[Minor] Update experiment name to include timestamp so that experiments are sorted in places like file systems.
#69 opened Jan 12, 2024 by eihli
1
Get BabyAI Datasets Working enhancement Improvements to existing features
#68 opened Jan 7, 2024 by eihli
@eihli
Training run with certain non-default values causes evaluation run to fail.
#66 opened Jan 3, 2024 by eihli
env.yml file specifies dependencies at build level, so it doesn't work straight away on Windows (and maybe other hosts)
#64 opened Dec 21, 2023 by SasankYadati
1
Investigate control data
#63 opened Dec 14, 2023 by snat-s Initial Release
@snat-s
Pick models to profile for the datasets
#62 opened Dec 14, 2023 by harshsikka
Profiling existing models
#61 opened Dec 14, 2023 by harshsikka
@harshsikka @snat-s
Outline Language & Vision Modality next steps
#60 opened Dec 11, 2023 by harshsikka
@bhavul
2
Outline Control Modality Next Steps across Data, Training
#59 opened Dec 11, 2023 by harshsikka
@jsjung00
3
v0 Dataset and Benchmark Specification
#58 opened Dec 11, 2023 by harshsikka
@harshsikka @snat-s
4
Updated Resource Analysis
#57 opened Dec 11, 2023 by harshsikka Initial Release
@harshsikka
Dataset Reconcilliation
#56 opened Dec 11, 2023 by harshsikka
@snat-s
1
Wandb tracking issue for distributed runs launched with accelerate.
#33 opened Nov 14, 2023 by eihli
Add code to cut sequence that is longer than context_len to fit in
#27 opened Oct 14, 2023 by henryj18
Better concatenation and individual metrics when using multiple text datasets enhancement Improvements to existing features good first issue Good for newcomers
#22 opened Oct 9, 2023 by bhavul
5
Add image-caption task into NEKO project
#20 opened Sep 27, 2023 by henryj18
1
Issues found in code review - series #1
#17 opened Sep 2, 2023 by henryj18
1
Parallel Batch Sampling
#13 opened Aug 17, 2023 by daniellawson9999
Atari Datasets
#12 opened Aug 15, 2023 by daniellawson9999
1
ProTip! Follow long discussions with comments:>50.