Add tutorial notebook

Example.ipynb

@@ -0,0 +1,113 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "5338af6d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import AutoModel, AutoTokenizer\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3e5e27fb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = AutoModel.from_pretrained(\"UF-NLPC-Lab/bart-stance-mixed\", trust_remote_code=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "eccdbd4e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokenizer = AutoTokenizer.from_pretrained(\"UF-NLPC-Lab/bart-stance-mixed\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "86cf1631",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# One claim target, and one noun-phrase target\n",
+    "# First prediction should be FAVOR, second should be NONE as the author says nothing about his opinion on salad itself.\n",
+    "samples = [\"Carrots are the superior vegetable.\", \"I don't like ranch on my salad.\"]\n",
+    "targets = [\"Brocoli is inferior to carrots.\", \"salad\"]\n",
+    "# Model was trained with target-then-sample. \n",
+    "encoding = tokenizer(text=targets, text_pair=samples, return_tensors='pt', padding=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "5d93f032",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output = model(**encoding)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "6a83f378",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['FAVOR', 'NONE']"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "logits = output.logits.detach().cpu().numpy()\n",
+    "preds = np.argmax(logits, axis=-1)\n",
+    "str_preds = [model.config.id2label[p] for p in preds]\n",
+    "str_preds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "26496ec3",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "min_transformers",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.22"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}