mirror of
https://github.com/rasbt/LLMs-from-scratch.git
synced 2025-11-13 16:45:32 +00:00
clarify truncation
This commit is contained in:
parent
4ac480c9ae
commit
1e12da90e6
@ -205,7 +205,10 @@
|
|||||||
"id": "fcc7c7a2-b6ab-478f-ae37-faa8eaa8049a",
|
"id": "fcc7c7a2-b6ab-478f-ae37-faa8eaa8049a",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/ch03_compressed/07.webp\" width=\"400px\">"
|
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/ch03_compressed/07.webp\" width=\"400px\">\n",
|
||||||
|
"\n",
|
||||||
|
"- (Please note that the numbers in this figure are truncated to one\n",
|
||||||
|
"digit after the decimal point to reduce visual clutter; similarly, other figures may also contain truncated values)"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -268,11 +271,13 @@
|
|||||||
"id": "299baef3-b1a8-49ba-bad4-f62c8a416d83",
|
"id": "299baef3-b1a8-49ba-bad4-f62c8a416d83",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
|
"- (In this book, we follow the common machine learning and deep learning convention where training examples are represented as rows and feature values as columns; in the caase of the tensor shown above, each row represents a word, and each column represents an embedding dimension)\n",
|
||||||
|
"\n",
|
||||||
"- The primary objective of this section is to demonstrate how the context vector $z^{(2)}$\n",
|
"- The primary objective of this section is to demonstrate how the context vector $z^{(2)}$\n",
|
||||||
" is calculated using the second input sequence, $x^{(2)}$, as a query\n",
|
" is calculated using the second input sequence, $x^{(2)}$, as a query\n",
|
||||||
"\n",
|
"\n",
|
||||||
"- The figure depicts the initial step in this process, which involves calculating the attention scores ω between $x^{(2)}$\n",
|
"- The figure depicts the initial step in this process, which involves calculating the attention scores ω between $x^{(2)}$\n",
|
||||||
" and all other input elements through a dot product operation."
|
" and all other input elements through a dot product operation"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -517,7 +522,10 @@
|
|||||||
"id": "11c0fb55-394f-42f4-ba07-d01ae5c98ab4",
|
"id": "11c0fb55-394f-42f4-ba07-d01ae5c98ab4",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/ch03_compressed/11.webp\" width=\"400px\">"
|
"<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/ch03_compressed/11.webp\" width=\"400px\">\n",
|
||||||
|
"\n",
|
||||||
|
"- (Please note that the numbers in this figure are truncated to two\n",
|
||||||
|
"digits after the decimal point to reduce visual clutter; the values in each row should add up to 1.0 or 100%; similarly, digits in other figures are truncated)"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -2019,7 +2027,7 @@
|
|||||||
"name": "python",
|
"name": "python",
|
||||||
"nbconvert_exporter": "python",
|
"nbconvert_exporter": "python",
|
||||||
"pygments_lexer": "ipython3",
|
"pygments_lexer": "ipython3",
|
||||||
"version": "3.11.4"
|
"version": "3.10.6"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"nbformat": 4,
|
"nbformat": 4,
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user