Skip to content

Commit 09c5b05

Browse files
committed
rearranging images
1 parent 3b15a98 commit 09c5b05

File tree

2 files changed

+1
-1
lines changed

2 files changed

+1
-1
lines changed
152 KB
Loading

docs/writing/posts/Karpathy's - let's build GPT from scratch.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -30,7 +30,7 @@ authors:
3030
Character level language model
3131
3232
Method: Bigram (Predict next char using previous char)
33-
![Pasted%20image%2020250130124540](Pasted%20image%2020250130124540.png)
33+
![Pasted%20image%2020250130124540](docs/writing/posts/img/Pasted%20image%2020250130124540.png)
3434
As seens above, it doesn't give good names. Bigram model is not good for predicting next character.
3535

3636
In "bigram" model probabilities become the parameter of bigram language model.

0 commit comments

Comments
 (0)