Skip to content

Pull requests: karpathy/nanoGPT

New pull request New
19 Open 57 Closed
19 Open 57 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Normalize the loss value to account for the number of gradient accumulation steps
#207 opened Mar 15, 2023 by chrisociepa Loading…
GPT2 dropout from huggingface is 0.1
#205 opened Mar 13, 2023 by Andrei-Aksionov Loading…
2
Model.py simplifications
#201 opened Mar 10, 2023 by Andrei-Aksionov Loading…
Add streaming output with minimal intervention.
#191 opened Mar 4, 2023 by AutomaticHourglass Loading…
1
Allow saving checkpoints for the best and the latest evaluation
#180 opened Feb 24, 2023 by chrisociepa Loading…
feat(project): add requirements
#173 opened Feb 21, 2023 by tpoisonooo Loading…
Add architecture diagram to README
#166 opened Feb 19, 2023 by bensu Loading…
Add Linear batch_size Scheduler
#160 opened Feb 18, 2023 by erikqu Loading…
4
Configurator will work correctly with default None values
#156 opened Feb 16, 2023 by Andrei-Aksionov Loading…
2
non flash attention: speedup by avoiding ddp broadcasts of causal mask
#151 opened Feb 15, 2023 by YassineYousfi Loading…
1
Add .gitignore
#146 opened Feb 13, 2023 by lutzroeder Loading…
Fix the position of a comma
#142 opened Feb 12, 2023 by kovkev Loading…
1
fix typo
#128 opened Feb 6, 2023 by abrahamsangha Loading…
Give love to tqdm too ;)
#101 opened Jan 30, 2023 by maraoz Loading…
1
Fix Issue with running prepare.py (modified repos/nanoGPT/data/openwebtext/prepare.py)
#80 opened Jan 22, 2023 by pierrebhat Loading…
1
4
Small fix to decode fn in shakespeare_char/prepare.py
#74 opened Jan 21, 2023 by venusatuluri Loading…
Give tqdm some love :)
#54 opened Jan 15, 2023 by MicroPanda123 Loading…
1
copy model args from checkpint model when resuming the training
#40 opened Jan 11, 2023 by yogi-miraje Loading…
batch file write
#10 opened Jan 2, 2023 by LaihoE Loading…
ProTip! Exclude everything labeled bug with -label:bug.