Skip to content

Issues: karpathy/ng-video-lecture

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

26 Open 4 Closed
26 Open 4 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

is this "m" forgotten?
#49 opened Oct 28, 2024 by yangyangyyy123
generated gibberish within the block
#48 opened Oct 10, 2024 by yangyangyyy123
Shouldn't we be dividing when normalizing QK^T, not multiplying?
#46 opened Sep 19, 2024 by tylerkastner
No MIT license file in the repository
#44 opened Jul 24, 2024 by matthewcarbone
The mathematical trick in self-attention, why it returns false for torch.allclose(xbow, xbow2)?
#43 opened Feb 28, 2024 by Ryan-ZL-Lin
2
Strange model behavior when taking the softmax in the wrong dimension
#42 opened Feb 14, 2024 by Cloud299
1
may you share code to run only inference
#40 opened Jan 21, 2024 by Sandy4321
2
supplementary video lecture: may you share link to this video pls
#39 opened Jan 21, 2024 by Sandy4321
2
can it be run on ubuntu PC with nvidia 3060 GPU 8 GB
#38 opened Jan 21, 2024 by Sandy4321
2
can be windows OS with only CPU used ?
#37 opened Jan 21, 2024 by Sandy4321
4
mac studio can't generate token
#35 opened Nov 1, 2023 by arthasyou
2
How is torch broadcasting (T, T) @ (B, T, C) ?!
#34 opened Oct 16, 2023 by whydna
4
gpt.py how to save the model after training and how to use it so that it returns the text to me relevant to ChatGPT?
#31 opened Sep 15, 2023 by MrKsiJ
5
wei value not 100% per row after dropout
#30 opened Sep 7, 2023 by guyko81
1
how to save, Load and Finetune the model
#29 opened Aug 25, 2023 by Lokeshwaran-M
1
Discrepancy with dimensions
#28 opened Aug 12, 2023 by BasedLukas
Change the Title Please
#25 opened Jul 16, 2023 by kentonbmax
Might want to modify README to remove the "NOTE"
#23 opened Jul 15, 2023 by zjmiller
About gpt.py line 134-135
#21 opened Jun 29, 2023 by hufuzhipeng
1
"index out of range" error when using a different embedding dimension than vocab_size
#20 opened Jun 19, 2023 by zhoupingjay
1
bug?: m vs model
#18 opened May 31, 2023 by freestylerick
6
Call model.eval() before generating?
#16 opened Apr 23, 2023 by gustavdelius
1
No license file
#15 opened Apr 4, 2023 by Maniues
1
no longer bigram model?
#5 opened Jan 24, 2023 by eniompw
1
pin
#4 opened Jan 22, 2023 by king22m
1
ProTip! Mix and match filters to narrow down what you’re looking for.