MR Feedback

Author: fryz

examples/summarize_scoring_using_bedrock.ipynb

@@ -248,7 +248,7 @@
     "\n",
     "# Make sure you've set the BENCH_FILE_DIR environment variable\n",
     "\n",
-    "# The summary_quality scorer uses ChatGPT to score the summary\n",
+    "# The summary_quality scorer uses gpt-3.5-turbo to score the summary\n",
     "# so make sure that your OPENAI_API_KEY environment variable is set\n",
     "\n",
     "combos = list(combinations(models, 2))\n",
@@ -302,15 +302,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "id": "1f1185e4-b39d-4107-bbc4-3aedc449cf46",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[('anthropic.claude-v2', 1345.4153155340496), ('meta.llama2-70b-chat-v1', 1079.6979024278733), ('amazon.titan-text-lite-v1', 898.4211374051577), ('anthropic.claude-v1', 864.5103513782595), ('meta.llama2-13b-chat-v1', 811.9552932546615)]\n"
+      "Model anthropic.claude-v2: Rating 1345.4153155340496\n",
+      "Model meta.llama2-70b-chat-v1: Rating 1079.6979024278733\n",
+      "Model amazon.titan-text-lite-v1: Rating 898.4211374051577\n",
+      "Model anthropic.claude-v1: Rating 864.5103513782595\n",
+      "Model meta.llama2-13b-chat-v1: Rating 811.9552932546615\n"
      ]
     }
    ],