Added some baselines

MinishLab · Oct 11, 2024 · ada8869 · ada8869
1 parent c3a5143
commit ada8869
Showing 1 changed file with 11 additions and 2 deletions.
diff --git a/tutorials/semantic_deduplication.ipynb b/tutorials/semantic_deduplication.ipynb
@@ -71,7 +71,7 @@
     "        deduplicated_text_indices.append(i)\n",
     "        seen.add(text)\n",
     "\n",
-    "len(deduplicated_text_indices)"
+    "print(\"Number of deduplicated docs:\", len(deduplicated_text_indices))"
    ]
   },
   {
@@ -260,7 +260,16 @@
    "cell_type": "code",
    "execution_count": 82,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of deduplicated docs: 119128\n",
+      "Time taken: 42.20003666699631\n"
+     ]
+    }
+   ],
    "source": [
     "wl = WordLlama.load()\n",
     "\n",