yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-01 18:30:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

100x -> 50x

Browse Source
This commit is contained in:
rasbt 2024-05-19 20:26:53 -05:00
parent 9512957b07
commit 5e1ba8343d
1 changed files with 1 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
appendix-E/01_main-chapter-code/appendix-E.ipynb
View File

@ -776,7 +776,7 @@
"id": "b8b6819e-ef7a-4f0d-841a-1b467496bef9"
},
"source": [
"- As we can see, we reduced the number of trainable parameters by almost 100x when using LoRA\n",
"- As we can see, we reduced the number of trainable parameters by almost 50x when using LoRA\n",
"- Let's now double-check whether the layers have been modified as intended by printing the model architecture"
]
},
@ -1474,14 +1474,6 @@
"source": [
"- As we can see based on the relatively high accuracy values above, the LoRA finetuning was successful"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "baa472da-44cf-42a9-8e59-6ddf7979bcd5",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {