added text summarization notebook

docs/notebooks/content/text_summerization_gpt.ipynb

@@ -0,0 +1,180 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4vXfYHX6QSJu"
+      },
+      "source": [
+        "<a target=\"_blank\" href=\"https://colab.research.google.com/github/gretelai/gretel-blueprints/blob/main/docs/notebooks/content/text_summerization_gpt.ipynb\">\n",
+        "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
+        "</a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Generate Synthetic text summarization with Gretel GPT\n",
+        "\n",
+        "* In this notebook we use Gretel GPT with Llama-2 7b model to create synthetic text summerization dataset.  \n",
+        "* To run this notebook, you will need an API key from the [Gretel Console](https://console.gretel.ai/users/me/key/)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "GhwZL2atTilv"
+      },
+      "source": [
+        "## Getting Started"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "V_iIkqnUQK2l"
+      },
+      "outputs": [],
+      "source": [
+        "%%capture\n",
+        "!pip install -U gretel-client"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "kixD67x_TSC4"
+      },
+      "outputs": [],
+      "source": [
+        "#import required packages\n",
+        "import pandas as pd\n",
+        "from gretel_client import Gretel"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0pMwi0RghUzh"
+      },
+      "source": [
+        "## Load and preview training data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 234
+        },
+        "id": "_QyG3jfRh2-i",
+        "outputId": "a60c1c7e-b71e-4843-cfb4-784000730546"
+      },
+      "outputs": [],
+      "source": [
+        "pd.set_option('max_colwidth', None)\n",
+        "\n",
+        "# Specify a dataset to train on\n",
+        "DATASET_PATH = 'https://gretel-datasets.s3.us-west-2.amazonaws.com/Text-dataset/Samsum-text-summerization-sample-1000.csv'\n",
+        "df = pd.read_csv(DATASET_PATH)\n",
+        "\n",
+        "#Let's look at the training dataset:\n",
+        "df.head()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Configure and Train the Synthetic Model:\n",
+        "\n",
+        "We can experiment different \"steps\" parameters which result in a change of text SQS."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "\n",
+        "\n",
+        "PROJECT = 'data-summarization'\n",
+        "LLM = \"meta-llama/Llama-2-7b-hf\"\n",
+        "\n",
+        "gretel = Gretel(project_name=f\"{PROJECT}-llama-2-7b\", api_key=\"prompt\", validate=True)\n",
+        "\n",
+        "trained = gretel.submit_train(\n",
+        "    \"natural-language\",\n",
+        "    data_source=df,\n",
+        "    pretrained_model=LLM,\n",
+        "    params={\"steps\": 1000}, \n",
+        " )"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Lh4-8dddoTWb"
+      },
+      "source": [
+        "## Display Text Synthetic Quality Score:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "trained.report.quality_scores"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "trained.report.display_in_notebook()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "J_yIE4WrW1Je"
+      },
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.9.17"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}