Readability and code quality improvements (#959)

* Consistent dataset naming

* consistent section headers
This commit is contained in:
Sebastian Raschka
2026-02-17 19:44:56 -05:00
committed by GitHub
parent 7b1f740f74
commit be5e2a3331
48 changed files with 419 additions and 297 deletions

View File

@@ -79,6 +79,7 @@
"id": "2417139b-2357-44d2-bd67-23f5d7f52ae7",
"metadata": {},
"source": [
" \n",
"## 2.1 Understanding word embeddings"
]
},
@@ -128,6 +129,7 @@
"id": "eddbb984-8d23-40c5-bbfa-c3c379e7eec3",
"metadata": {},
"source": [
" \n",
"## 2.2 Tokenizing text"
]
},
@@ -445,6 +447,7 @@
"id": "0b5ce8fe-3a07-4f2a-90f1-a0321ce3a231",
"metadata": {},
"source": [
" \n",
"## 2.3 Converting tokens into token IDs"
]
},
@@ -738,6 +741,7 @@
"id": "4b821ef8-4d53-43b6-a2b2-aef808c343c7",
"metadata": {},
"source": [
" \n",
"## 2.4 Adding special context tokens"
]
},
@@ -1013,6 +1017,7 @@
"id": "5c4ba34b-170f-4e71-939b-77aabb776f14",
"metadata": {},
"source": [
" \n",
"## 2.5 BytePair encoding"
]
},
@@ -1528,6 +1533,7 @@
"id": "2cd2fcda-2fda-4aa8-8bc8-de1e496f9db1",
"metadata": {},
"source": [
" \n",
"## 2.7 Creating token embeddings"
]
},
@@ -1715,6 +1721,7 @@
"id": "c393d270-b950-4bc8-99ea-97d74f2ea0f6",
"metadata": {},
"source": [
" \n",
"## 2.8 Encoding word positions"
]
},
@@ -1945,7 +1952,8 @@
"id": "63230f2e-258f-4497-9e2e-8deee4530364",
"metadata": {},
"source": [
"# Summary and takeaways"
" \n",
"## Summary and takeaways"
]
},
{
@@ -1977,7 +1985,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.16"
"version": "3.13.5"
}
},
"nbformat": 4,