Giters
karpathy
/
ng-video-lecture
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
3006
Watchers:
48
Issues:
26
Forks:
778
karpathy/ng-video-lecture Issues
The mathematical trick in self-attention, why it returns false for torch.allclose(xbow, xbow2)?
Updated
a month ago
Comments count
1
bug?: m vs model
Updated
a month ago
Comments count
6
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?
Updated
2 months ago
Comments count
5
Strange model behavior when taking the softmax in the wrong dimension
Updated
2 months ago
supplementary video lecture: may you share link to this video pls
Updated
2 months ago
Comments count
2
can be windows OS with only CPU used ?
Updated
2 months ago
Comments count
2
can it be run on ubuntu PC with nvidia 3060 GPU 8 GB
Updated
2 months ago
Comments count
2
may you share code to run only inference
Updated
2 months ago
Comments count
2
About gpt.py line 134-135
Updated
2 months ago
Comments count
1
wei value not 100% per row after dropout
Updated
3 months ago
Comments count
1
mac studio can't generate token
Updated
3 months ago
Comments count
2
Using the variable "model" after declaring variable "m"
Closed
3 months ago
Comments count
1
how to save, Load and Finetune the model
Updated
4 months ago
Comments count
1
How is torch broadcasting (T, T) @ (B, T, C) ?!
Updated
6 months ago
Comments count
4
KeyError
Closed
7 months ago
Discrepancy with dimensions
Updated
8 months ago
Change the Title Please
Updated
9 months ago
Position embedding seems wrong
Closed
9 months ago
Might want to modify README to remove the "NOTE"
Updated
9 months ago
No license file
Updated
10 months ago
Comments count
1
pin
Updated
10 months ago
Comments count
1
UML diagram helping beginners understand gpt.py
Updated
10 months ago
Comments count
2
"index out of range" error when using a different embedding dimension than vocab_size
Updated
10 months ago
Comments count
1
Call `model.eval()` before generating?
Updated
a year ago
Comments count
1
time series data like BTC price
Updated
a year ago
Comments count
1
no longer bigram model?
Updated
a year ago
Comments count
1