prabha-git
diff --git a/‎assets/images/Pasted.md‎ b/‎assets/images/Pasted.md‎
diff --git a/‎docs/writing/posts/Karpathy's - let's build GPT from scratch.md‎
Lines changed: 1 addition & 1 deletion b/‎docs/writing/posts/Karpathy's - let's build GPT from scratch.md‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎assets/images/Pasted image 20250130124540.png‎ renamed to ‎docs/writing/posts/img/Pasted image 20250130124540.png‎ b/‎assets/images/Pasted image 20250130124540.png‎ renamed to ‎docs/writing/posts/img/Pasted image 20250130124540.png‎
diff --git a/‎assets/images/Pasted image 20250205123847.png‎ renamed to ‎docs/writing/posts/img/Pasted image 20250205123847.png‎ b/‎assets/images/Pasted image 20250205123847.png‎ renamed to ‎docs/writing/posts/img/Pasted image 20250205123847.png‎
@@ -30,7 +30,7 @@ authors:
 		Character level language model
 		
 		Method: Bigram (Predict next char using previous char)
-![Pasted%20image%2020250130124540](assets/images/Pasted%20image%2020250130124540.png)
+![Pasted%20image%2020250130124540](Pasted%20image%2020250130124540.png)
 	As seens above, it doesn't give good names. Bigram model is not good for predicting next character.
 
 	In "bigram" model probabilities become the parameter of bigram language model.