From f6260a013e1af27ca82a3bf0a390451173e1d4f2 Mon Sep 17 00:00:00 2001
From: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com>
Date: Fri, 29 Sep 2023 06:20:32 +0530
Subject: [PATCH] fix: typo in hallucination reduction stat (#742)

---
 .../ft_retrieval_augmented_generation_qdrant.ipynb              | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/examples/fine-tuned_qa/ft_retrieval_augmented_generation_qdrant.ipynb b/examples/fine-tuned_qa/ft_retrieval_augmented_generation_qdrant.ipynb
index 25b911b..9d0a073 100644
--- a/examples/fine-tuned_qa/ft_retrieval_augmented_generation_qdrant.ipynb
+++ b/examples/fine-tuned_qa/ft_retrieval_augmented_generation_qdrant.ipynb
@@ -871,7 +871,7 @@
     "### Observations\n",
     "\n",
     "1. The fine-tuned model is better at saying \"I don't know\"\n",
-    "2. Hallucinations drop from 100% to 0% with fine-tuning\n",
+    "2. Hallucinations drop from 100% to 15% with fine-tuning\n",
     "3. Wrong answers drop from 17% to 6% with fine-tuning\n",
     "\n",
     "**Correct answers also drop from 83% to 60% with fine-tuning** - this is because the fine-tuned model is **more conservative** and says \"I don't know\" more often. This is a good thing because it's better to say \"I don't know\" than to give a wrong answer.\n",