{
"cells": [
{
"cell_type": "markdown",
"id": "ec0e737f",
"metadata": {},
"source": [
"\n",
" \n",
""
]
},
{
"cell_type": "markdown",
"id": "ab8ae3fe",
"metadata": {},
"source": [
"# Prompt Engineering\n",
"\n",
"This notebook focuses on how to design prompts that produce useful, reproducible, and well-formatted outputs. The central idea is not using magic words, but reducing ambiguity and giving the model a clear target.\n",
"\n",
"**Suggested duration:** 2.5 hours"
]
},
{
"cell_type": "markdown",
"id": "b29c9187",
"metadata": {},
"source": [
"
A) Ask the same prompts (weak and strong) to Chatgpt?
\n", "B) Try different models:
\n",
"- `google/flan-t5-base`: stronger than the small version, still manageable for demonstrations.
\n",
"- `distilgpt2`: useful to show the limits of a non-instruction-tuned model.
\n",
"
Request the other table_prompt with another free model
\n", "