git-market/rasbt-LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-14 03:11:40 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #1 from rasbt/main

Browse Source 
Fork Sync: Update from parent repository
This commit is contained in:
github-actions[bot] 2026-02-19 04:46:51 +00:00 committed by GitHub
commit c195785faa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 22 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
appendix-A/01_main-chapter-code/code-part1.ipynb
View File

@ -1168,7 +1168,7 @@
"source": [
"def compute_accuracy(model, dataloader):\n",
"\n",
" model = model.eval()\n",
" model.eval()\n",
" correct = 0.0\n",
" total_examples = 0\n",
" \n",
@ -1340,7 +1340,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.11"
"version": "3.13.5"
}
},
"nbformat": 4,

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",

2
reasoning-from-scratch

@ -1 +1 @@
Subproject commit edcae1d894192a2d7c036bfea43922cb140dea10
Subproject commit 7b6a9d0f9090201dcb66c6242812d29aec379c77