jim/openai-cookbook
1
0
Fork 0
mirror of https://github.com/james-m-jordan/openai-cookbook.git synced 2025-05-09 19:32:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: typo in hallucination reduction stat (#742)

Browse Source
This commit is contained in:
Dhruv Anand 2023-09-29 06:20:32 +05:30 committed by GitHub
parent c3f5e0cd7c
commit f6260a013e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/fine-tuned_qa/ft_retrieval_augmented_generation_qdrant.ipynb
View File

@ -871,7 +871,7 @@
"### Observations\n", "### Observations\n",
"\n", "\n",
"1. The fine-tuned model is better at saying \"I don't know\"\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", "3. Wrong answers drop from 17% to 6% with fine-tuning\n",
"\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", "**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",