Merge pull request #496 from elizjo/main

Notebook support for generalml_p311_cpu_x86_64_v1 conda pack

Author: darenr

notebook_examples/README.md

@@ -1,5 +1,23 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "fac705fa",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "@notebook{aqua-batch-inferencing.ipynb,\n",
+    "    title: AI Quick Action - Batch inferencing,\n",
+    "    summary: Perform batch inferencing on LLMs using AI Quick Actions.,\n",
+    "    developed_on: generalml_p311_cpu_x86_64_v1,\n",
+    "    keywords: quick action, batch, inferencing, llm\n",
+    "    license: Universal Permissive License v 1.0\n",
+    "}"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "f9990553-e6f8-4293-b89e-946f3e4c17e3",

notebook_examples/aqua-batch-inferencing.ipynb

@@ -1,13 +1,31 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "748139a6",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "@notebook{aqua-deploy-llm-byoc.ipynb,\n",
+    "    title: Deploy LLM Models using BYOC,\n",
+    "    summary: Deploy and perform inferencing using AI Quick Action models.,\n",
+    "    developed_on: generalml_p311_cpu_x86_64_v1,\n",
+    "    keywords: byoc, llm, quick action, deploy\n",
+    "    license: Universal Permissive License v 1.0\n",
+    "}"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "443c3053",
    "metadata": {},
    "source": [
     "# Deploy LLM Models using BYOC\n",
     "\n",
-    "This guide demonstrates how to deploy and perform inference using AI Quick Action registered models with Oracle Data Science Service Managed Containers (SMC) powered by vLLM. In this example, we will use a model downloaded from Hugging Face specifically, [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) from Meta. \n"
+    "This guide demonstrates how to deploy and perform inferencing using AI Quick Action registered models with Oracle Data Science Service Managed Containers (SMC) powered by vLLM. In this example, we will use a model downloaded from Hugging Face specifically, [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) from Meta. \n"
    ]
   },
   {