issues
search
karpathy
/
ng-video-lecture
3.46k
stars
902
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Shouldn't we be dividing when normalizing QK^T, not multiplying?
#46
tylerkastner
opened
1 week ago
0
refactor: linting
#45
shivakumarmahesh
closed
3 weeks ago
0
No MIT license file in the repository
#44
matthewcarbone
opened
2 months ago
0
The mathematical trick in self-attention, why it returns false for torch.allclose(xbow, xbow2)?
#43
Ryan-ZL-Lin
opened
7 months ago
2
Strange model behavior when taking the softmax in the wrong dimension
#42
Cloud299
opened
7 months ago
1
disabled gradient calculation in generate function (bigram.py)
#41
arun477
opened
8 months ago
1
may you share code to run only inference
#40
Sandy4321
opened
8 months ago
2
supplementary video lecture: may you share link to this video pls
#39
Sandy4321
opened
8 months ago
2
can it be run on ubuntu PC with nvidia 3060 GPU 8 GB
#38
Sandy4321
opened
8 months ago
2
can be windows OS with only CPU used ?
#37
Sandy4321
opened
8 months ago
4
Using the variable "model" after declaring variable "m"
#36
klivin
closed
8 months ago
1
mac studio can't generate token
#35
arthasyou
opened
11 months ago
2
How is torch broadcasting (T, T) @ (B, T, C) ?!
#34
whydna
opened
11 months ago
4
Dev
#33
jhancock1975
closed
11 months ago
2
KeyError
#32
yihaoye
closed
1 year ago
0
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
MrKsiJ
opened
1 year ago
5
wei value not 100% per row after dropout
#30
guyko81
opened
1 year ago
1
how to save, Load and Finetune the model
#29
Lokeshwaran-M
opened
1 year ago
1
Discrepancy with dimensions
#28
BasedLukas
opened
1 year ago
0
edit shape comments in `generate` method
#27
cthiriet
closed
6 months ago
0
M1/M2 performance fix: use Apple MPS (metal performance shaders) if available
#26
sghael
opened
1 year ago
3
Change the Title Please
#25
kentonbmax
opened
1 year ago
0
Position embedding seems wrong
#24
zurtal
closed
1 year ago
0
Might want to modify README to remove the "NOTE"
#23
zjmiller
opened
1 year ago
0
Minor correction in 'Add & Norm' logic in Block Class in gpt.py
#22
AbhishekAshokDubey
opened
1 year ago
1
About gpt.py line 134-135
#21
hufuzhipeng
opened
1 year ago
1
"index out of range" error when using a different embedding dimension than vocab_size
#20
zhoupingjay
opened
1 year ago
1
Merge #1
#19
yrraadi-io
closed
1 year ago
0
bug?: m vs model
#18
freestylerick
opened
1 year ago
6
updated dictionary names
#17
caaker
opened
1 year ago
1
Call `model.eval()` before generating?
#16
gustavdelius
opened
1 year ago
1
No license file
#15
Maniues
opened
1 year ago
1
time series data like BTC price
#14
tesla-cat
closed
1 month ago
1
Adding architecture diagram for nanogpt
#13
patchy631
opened
1 year ago
0
adding option to use the bpe tokenizer tiktoken as mentioned in the lecture
#12
jhlimm8
closed
1 year ago
2
Teeny-tiny performance improvement
#11
Andrei-Aksionov
opened
1 year ago
0
Loss calculation should not permanently change shapes of logits and targets
#10
Andrei-Aksionov
opened
1 year ago
0
Clarify shape descriptions inside forward method
#9
Andrei-Aksionov
closed
1 year ago
2
Add Keras Counterparts
#8
j-planet
opened
1 year ago
0
removes unnecessary duplicate variable
#7
hoosha
opened
1 year ago
1
We should scale attention by head size
#6
vineetm
closed
1 year ago
1
no longer bigram model?
#5
eniompw
opened
1 year ago
1
pin
#4
king22m
opened
1 year ago
1
Automating data download if needed
#3
nicholas-dinicola
opened
1 year ago
0
UML diagram helping beginners understand gpt.py
#2
QasimWani
opened
1 year ago
2
fix linting errors
#1
mendi80
opened
1 year ago
0