Fix llm as a judge cookbook images (#1517)

2025-05-09 19:32:38 +00:00 · 2024-10-24 23:14:32 -07:00 · 2024-10-24 23:14:32 -07:00 · e19a3725a9
commit e19a3725a9
parent fe2bbf14cb
5 changed files with 3 additions and 3 deletions
--- a/examples/Custom-LLM-as-a-Judge.ipynb
+++ b/examples/Custom-LLM-as-a-Judge.ipynb
@ -499,7 +499,7 @@
    "It looks like the numeric rater scored almost 94% in total. That's not bad, but if 6% of your evals are incorrectly judged, that could make it very hard to trust them. Let's dig into the Braintrust\n",
    "UI to get some insight into what's going on.\n",
    "\n",
-    "![Partial credit](../images/Custom-LLM-as-a-Judge/Partial-Credit.gif)\n",
+    "![Partial credit](../images/Custom-LLM-as-a-Judge-Partial-Credit.gif)\n",
    "\n",
    "It looks like a number of the incorrect answers were scored with numbers between 1 and 10. However, we do not currently have any insight into why the model gave these scores. Let's see if we can\n",
    "fix that next.\n"
@ -670,11 +670,11 @@
    "It doesn't look like adding reasoning helped the score (in fact, it's half a percent worse). However, if we look at one of the failures, we'll get some insight into\n",
    "what the model was thinking. Here is an example of a hallucinated answer:\n",
    "\n",
-    "![Output](../images/Custom-LLM-as-a-Judge/Output.png)\n",
+    "![Output](../images/Custom-LLM-as-a-Judge-Output.png)\n",
    "\n",
    "And the score along with its reasoning:\n",
    "\n",
-    "![Reasoning](../images/Custom-LLM-as-a-Judge/Reasoning.png)\n"
+    "![Reasoning](../images/Custom-LLM-as-a-Judge-Reasoning.png)\n"
   ]
  },
  {
--- a/images/Custom-LLM-as-a-Judge-Output.png
+++ b/images/Custom-LLM-as-a-Judge-Output.png
--- a/images/Custom-LLM-as-a-Judge-Partial-Credit.gif
+++ b/images/Custom-LLM-as-a-Judge-Partial-Credit.gif
--- a/images/Custom-LLM-as-a-Judge-Reasoning.png
+++ b/images/Custom-LLM-as-a-Judge-Reasoning.png
--- a/images/Custom-LLM-as-a-Judge/Classifier.png
+++ b/images/Custom-LLM-as-a-Judge/Classifier.png