Add Execution Counts (#177)

* Update notebooks * Update FastEmbed usage across docs * Refactor code for better readability and maintainability * Clean outputs * Change dataset * Add numbers inline in output * Remove inline outputs since I used :memory: * Fix syntax error in Hindi_Tamil_RAG_with_Navarasa7B.ipynb
qdrant · Apr 1, 2024 · c099097 · c099097
1 parent 3d2254d
commit c099097
Show file tree

Hide file tree

Showing 6 changed files with 254 additions and 1,366 deletions.
diff --git a/docs/examples/FastEmbed_vs_HF_Comparison.ipynb b/docs/examples/FastEmbed_vs_HF_Comparison.ipynb
diff --git a/docs/examples/Hindi_Tamil_RAG_with_Navarasa7B.ipynb b/docs/examples/Hindi_Tamil_RAG_with_Navarasa7B.ipynb
@@ -22,28 +22,39 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
    "metadata": {
     "id": "rOTVBRFAj2U-"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
+      "To disable this warning, you can either:\n",
+      "\t- Avoid using `tokenizers` before the fork if possible\n",
+      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
+     ]
+    }
+   ],
    "source": [
     "!pip install -U fastembed datasets qdrant-client peft transformers accelerate bitsandbytes -qq"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 21,
    "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-30T00:45:24.814968Z",
+     "start_time": "2024-03-30T00:45:24.811138Z"
+    },
     "colab": {
      "base_uri": "https://localhost:8080/"
     },
     "id": "aAfdPG15j2U_",
-    "outputId": "c457a5dd-bccb-4b56-8c7f-878dfc94884d",
-    "ExecuteTime": {
-     "end_time": "2024-03-30T00:45:24.814968Z",
-     "start_time": "2024-03-30T00:45:24.811138Z"
-    }
+    "outputId": "c457a5dd-bccb-4b56-8c7f-878dfc94884d"
    },
    "outputs": [],
    "source": [
@@ -61,11 +72,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
-    "hf_token = \"<YOUR_HF_TOKEN_HERE>\"  # Get your token from https://huggingface.co/settings/token, needed for Gemma weights"
+    "hf_token = <YOUR_HF_TOKEN_HERE>  # Get your token from https://huggingface.co/settings/token, needed for Gemma weights"
    ]
   },
   {
@@ -88,7 +99,7 @@
    "outputs": [],
    "source": [
     "embedding_model = \"sentence-transformers/paraphrase-multilingual-mpnet-base-v2\"\n",
-    "model_id = \"Telugu-LLM-Labs/Indic-gemma-7b-finetuned-sft-Navarasa\""
+    "model_id = \"Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa\""
    ]
   },
   {
@@ -451,9 +462,9 @@
    "provenance": []
   },
   "kernelspec": {
-   "name": "python3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "display_name": "Python 3 (ipykernel)"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {