books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

adjust figure width

Browse Source
This commit is contained in:
rasbt
2024-02-04 10:09:36 -06:00
parent f2fe1d0d85
commit 1653f6953a
1 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
ch04/01_main-chapter-code/ch04.ipynb
View File

@@ -21,7 +21,7 @@
"id": "7d4f11e0-4434-4979-9dee-e1207df0eb01",
"metadata": {},
"source": [
"<img src=\"figures/mental-model.webp\" width=700px>"
"<img src=\"figures/mental-model.webp\" width=500px>"
]
},
{
@@ -48,7 +48,7 @@
"id": "5c5213e9-bd1c-437e-aee8-f5e8fb717251",
"metadata": {},
"source": [
"<img src=\"figures/mental-model-2.webp\" width=500px>"
"<img src=\"figures/mental-model-2.webp\" width=300px>"
]
},
{
@@ -173,7 +173,7 @@
"id": "9665e8ab-20ca-4100-b9b9-50d9bdee33be",
"metadata": {},
"source": [
"<img src=\"figures/gpt-in-out.webp\" width=600px>"
"<img src=\"figures/gpt-in-out.webp\" width=300px>"
]
},
{
@@ -271,7 +271,7 @@
"id": "314ac47a-69cc-4597-beeb-65bed3b5910f",
"metadata": {},
"source": [
"<img src=\"figures/layernorm.webp\" width=500px>"
"<img src=\"figures/layernorm.webp\" width=300px>"
]
},
{
@@ -357,7 +357,7 @@
"id": "570db83a-205c-4f6f-b219-1f6195dde1a7",
"metadata": {},
"source": [
"<img src=\"figures/layernorm2.webp\" width=400px>"
"<img src=\"figures/layernorm2.webp\" width=300px>"
]
},
{
@@ -528,7 +528,7 @@
"id": "e136cfc4-7c89-492e-b120-758c272bca8c",
"metadata": {},
"source": [
"<img src=\"figures/overview-after-ln.webp\" width=500px>"
"<img src=\"figures/overview-after-ln.webp\" width=300px>"
]
},
{
@@ -673,7 +673,7 @@
"id": "fdcaacfa-3cfc-4c9e-b668-b71a2753145a",
"metadata": {},
"source": [
"<img src=\"figures/ffn.webp\" width=400px>"
"<img src=\"figures/ffn.webp\" width=300px>"
]
},
{
@@ -725,7 +725,7 @@
"- This is achieved by adding the output of one layer to the output of a later layer, usually skipping one or more layers in between\n",
"- Let's illustrate this idea with a small example network:\n",
"\n",
"<img src=\"figures/shortcut-example.webp\" width=500px>"
"<img src=\"figures/shortcut-example.webp\" width=300px>"
]
},
{
@@ -849,7 +849,7 @@
"id": "36b64d16-94a6-4d13-8c85-9494c50478a9",
"metadata": {},
"source": [
"<img src=\"figures/transformer-block.webp\" width=500px>"
"<img src=\"figures/transformer-block.webp\" width=300px>"
]
},
{
@@ -909,7 +909,7 @@
"id": "9b7b362d-f8c5-48d2-8ebd-722480ac5073",
"metadata": {},
"source": [
"<img src=\"figures/gpt.webp\" width=500px>"
"<img src=\"figures/gpt.webp\" width=300px>"
]
},
{
@@ -1153,7 +1153,7 @@
"id": "0042c58e-995a-4a42-887f-613cad9f22b9",
"metadata": {},
"source": [
"<img src=\"figures/mental-model-final.webp\" width=500px>"
"<img src=\"figures/mental-model-final.webp\" width=300px>"
]
},
{
@@ -1177,7 +1177,7 @@
"id": "caade12a-fe97-480f-939c-87d24044edff",
"metadata": {},
"source": [
"<img src=\"figures/iterative-gen.webp\" width=500px>"
"<img src=\"figures/iterative-gen.webp\" width=300px>"
]
},
{
@@ -1239,7 +1239,7 @@
"source": [
"- The `generate_text_simple` above implements an iterative process, where it creates one token at a time\n",
"\n",
"<img src=\"figures/iterative-generate.webp\" width=600px>"
"<img src=\"figures/iterative-generate.webp\" width=400px>"
]
},
{