align formulas in notes with code (#605)

rasbt · web-flow · commit 3654571184b6 · 2025-04-06T16:46:53.000-05:00
diff --git a/ch03/01_main-chapter-code/ch03.ipynb b/ch03/01_main-chapter-code/ch03.ipynb
@@ -797,9 +797,9 @@
     "- Implementing the self-attention mechanism step by step, we will start by introducing the three training weight matrices $W_q$, $W_k$, and $W_v$\n",
     "- These three matrices are used to project the embedded input tokens, $x^{(i)}$, into query, key, and value vectors via matrix multiplication:\n",
     "\n",
-    "  - Query vector: $q^{(i)} = W_q \\,x^{(i)}$\n",
-    "  - Key vector: $k^{(i)} = W_k \\,x^{(i)}$\n",
-    "  - Value vector: $v^{(i)} = W_v \\,x^{(i)}$\n"
+    "  - Query vector: $q^{(i)} = x^{(i)}\\,W_q $\n",
+    "  - Key vector: $k^{(i)} = x^{(i)}\\,W_k $\n",
+    "  - Value vector: $v^{(i)} = x^{(i)}\\,W_v $\n"
    ]
   },
   {

Original file line number	Diff line number	Diff line change
`@@ -797,9 +797,9 @@`
`797`	`797`	`"- Implementing the self-attention mechanism step by step, we will start by introducing the three training weight matrices $W_q$, $W_k$, and $W_v$\n",`
`798`	`798`	`"- These three matrices are used to project the embedded input tokens, $x^{(i)}$, into query, key, and value vectors via matrix multiplication:\n",`
`799`	`799`	`"\n",`
`800`		`- " - Query vector: $q^{(i)} = W_q \\,x^{(i)}$\n",`
`801`		`- " - Key vector: $k^{(i)} = W_k \\,x^{(i)}$\n",`
`802`		`- " - Value vector: $v^{(i)} = W_v \\,x^{(i)}$\n"`
	`800`	`+ " - Query vector: $q^{(i)} = x^{(i)}\\,W_q $\n",`
	`801`	`+ " - Key vector: $k^{(i)} = x^{(i)}\\,W_k $\n",`
	`802`	`+ " - Value vector: $v^{(i)} = x^{(i)}\\,W_v $\n"`
`803`	`803`	`]`
`804`	`804`	`},`
`805`	`805`	`{`