|
|
@ -16,7 +16,9 @@
|
|
|
|
"# Introduction to Weight Quantization\n",
|
|
|
|
"# Introduction to Weight Quantization\n",
|
|
|
|
"> Reducing the size of Large Language Models with 8-bit quantization\n",
|
|
|
|
"> Reducing the size of Large Language Models with 8-bit quantization\n",
|
|
|
|
"\n",
|
|
|
|
"\n",
|
|
|
|
"❤️ Created by [@maximelabonne](https://twitter.com/maximelabonne)."
|
|
|
|
"❤️ Created by [@maximelabonne](https://twitter.com/maximelabonne).\n",
|
|
|
|
|
|
|
|
"\n",
|
|
|
|
|
|
|
|
"Companion notebook to execute the code from the following article: https://mlabonne.github.io/blog/intro_weight_quantization/"
|
|
|
|
],
|
|
|
|
],
|
|
|
|
"metadata": {
|
|
|
|
"metadata": {
|
|
|
|
"id": "yG1VY-TJoxix"
|
|
|
|
"id": "yG1VY-TJoxix"
|
|
|
|