Update RFT_demo.ipynb

Author: maciejskorski

src/RFT_demo.ipynb

@@ -4,11 +4,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "[![nbviewer](https://raw.githubusercontent.com/jupyter/design/master/logos/Badges/nbviewer_badge.svg)](https://nbviewer.org/github/maciejskorski/ml_examples/blob/master/src/RFT_demo.ipynb)",
     "# Summary\n",
     "\n",
-    "This experiment uses reinforcement fine-tunning (RFT) service of OpenAI to fine-tune one of their modes for emotion recognition.\n",
+    "This experiment uses the reinforcement fine-tunning (RFT) service of OpenAI to fine-tune one of their modes for better emotion recognition.\n",
     "\n",
-    "Emotion recognition is a subjective multilabel classification problem, on which LLMs suffer from overly sparse predictions."
+    "Note: Emotion recognition is a subjective multilabel classification problem, on which LLMs suffer from overly sparse predictions."
    ]
   },
   {