git-market/rasbt-LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-11 14:21:41 +08:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Use correct example in layernorm section

Browse Source
This commit is contained in:
rasbt 2026-02-18 21:24:20 -06:00
parent 1ba7bd5c04
commit 883f6d0702
No known key found for this signature in database
1 changed files with 19 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
ch04/01_main-chapter-code/ch04.ipynb
View File

@ -38,9 +38,9 @@
"name": "stdout",
"output_type": "stream",
"text": [
"matplotlib version: 3.10.0\n",
"torch version: 2.6.0\n",
"tiktoken version: 0.9.0\n"
"matplotlib version: 3.10.8\n",
"torch version: 2.10.0\n",
"tiktoken version: 0.12.0\n"
]
}
],
@ -492,8 +492,8 @@
"output_type": "stream",
"text": [
"Mean:\n",
" tensor([[ -0.0000],\n",
" [ 0.0000]], grad_fn=<MeanBackward1>)\n",
" tensor([[-0.0000],\n",
" [ 0.0000]], grad_fn=<MeanBackward1>)\n",
"Variance:\n",
" tensor([[1.0000],\n",
" [1.0000]], grad_fn=<VarBackward0>)\n"
@ -564,8 +564,8 @@
"metadata": {},
"outputs": [],
"source": [
"ln = LayerNorm(emb_dim=5)\n",
"out_ln = ln(batch_example)"
"ln = LayerNorm(emb_dim=6)\n",
"out_ln = ln(out)"
]
},
{
@ -579,11 +579,11 @@
"output_type": "stream",
"text": [
"Mean:\n",
" tensor([[ -0.0000],\n",
" [ 0.0000]], grad_fn=<MeanBackward1>)\n",
" tensor([[-0.0000],\n",
" [-0.0000]], grad_fn=<MeanBackward1>)\n",
"Variance:\n",
" tensor([[1.0000],\n",
" [1.0000]], grad_fn=<VarBackward0>)\n"
" tensor([[0.9995],\n",
" [0.9997]], grad_fn=<VarBackward0>)\n"
]
}
],
@ -595,6 +595,14 @@
"print(\"Variance:\\n\", var)"
]
},
{
"cell_type": "markdown",
"id": "07220af7-cf53-48c8-8831-813a7088edea",
"metadata": {},
"source": [
"- Variance is not exactly 1 because we use `eps`"
]
},
{
"cell_type": "markdown",
"id": "e136cfc4-7c89-492e-b120-758c272bca8c",