{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "003973a6",
   "metadata": {},
   "source": [
    "## Save model to S3 storage"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9ae08384",
   "metadata": {},
   "source": [
    "### Import Caikit-NLP"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d758b7e4-c8c1-4c7f-82a2-2cbf5e580a96",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cloning into 'caikit-nlp'...\n",
      "remote: Enumerating objects: 5954, done.\u001b[K\n",
      "remote: Counting objects: 100% (643/643), done.\u001b[K\n",
      "remote: Compressing objects: 100% (222/222), done.\u001b[K\n",
      "remote: Total 5954 (delta 444), reused 546 (delta 403), pack-reused 5311\u001b[K\n",
      "Receiving objects: 100% (5954/5954), 2.56 MiB | 27.03 MiB/s, done.\n",
      "Resolving deltas: 100% (4361/4361), done.\n"
     ]
    }
   ],
   "source": [
    "!git clone https://github.com/caikit/caikit-nlp.git"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "2bce9855-3ea3-48ed-b3f4-5927fc047d6a",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processing ./caikit-nlp\n",
      "  Installing build dependencies ... \u001b[?25ldone\n",
      "\u001b[?25h\u001b[33m  WARNING: Missing build requirements in pyproject.toml for file:///opt/app-root/src/notebooks/caikit-nlp.\u001b[0m\u001b[33m\n",
      "\u001b[0m\u001b[33m  WARNING: The project does not specify a build backend, and pip cannot fall back to setuptools without 'wheel'.\u001b[0m\u001b[33m\n",
      "\u001b[0m  Getting requirements to build wheel ... \u001b[?25ldone\n",
      "\u001b[?25h  Installing backend dependencies ... \u001b[?25ldone\n",
      "\u001b[?25h  Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
      "\u001b[?25hRequirement already satisfied: numpy>=1.22.4 in /opt/app-root/lib/python3.9/site-packages (from caikit-nlp==0.4.9.dev2+gc12cb82) (1.24.4)\n",
      "Collecting caikit-tgis-backend<0.2.0,>=0.1.27\n",
      "  Downloading caikit_tgis_backend-0.1.31-py3-none-any.whl (29 kB)\n",
      "Collecting huggingface-hub\n",
      "  Downloading huggingface_hub-0.22.2-py3-none-any.whl (388 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m388.9/388.9 kB\u001b[0m \u001b[31m45.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting transformers>=4.32.0\n",
      "  Downloading transformers-4.40.1-py3-none-any.whl (9.0 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.0/9.0 MB\u001b[0m \u001b[31m221.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hCollecting datasets>=2.4.0\n",
      "  Downloading datasets-2.19.0-py3-none-any.whl (542 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m542.0/542.0 kB\u001b[0m \u001b[31m331.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: torch>=2.0.1 in /opt/app-root/lib/python3.9/site-packages (from caikit-nlp==0.4.9.dev2+gc12cb82) (2.0.1+cu118)\n",
      "Requirement already satisfied: pandas>=1.5.0 in /opt/app-root/lib/python3.9/site-packages (from caikit-nlp==0.4.9.dev2+gc12cb82) (1.5.3)\n",
      "Requirement already satisfied: tqdm>=4.65.0 in /opt/app-root/lib/python3.9/site-packages (from caikit-nlp==0.4.9.dev2+gc12cb82) (4.66.2)\n",
      "Requirement already satisfied: scipy>=1.8.1 in /opt/app-root/lib/python3.9/site-packages (from caikit-nlp==0.4.9.dev2+gc12cb82) (1.11.4)\n",
      "Collecting tokenizers>=0.13.3\n",
      "  Downloading tokenizers-0.19.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.6 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m320.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting accelerate>=0.22.0\n",
      "  Downloading accelerate-0.29.3-py3-none-any.whl (297 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m297.6/297.6 kB\u001b[0m \u001b[31m305.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: scikit-learn>=1.1 in /opt/app-root/lib/python3.9/site-packages (from caikit-nlp==0.4.9.dev2+gc12cb82) (1.3.2)\n",
      "Collecting caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17\n",
      "  Downloading caikit-0.26.20-py3-none-any.whl (419 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m419.9/419.9 kB\u001b[0m \u001b[31m304.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting peft==0.6.0\n",
      "  Downloading peft-0.6.0-py3-none-any.whl (134 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.9/134.9 kB\u001b[0m \u001b[31m158.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting sentence-transformers<2.4.0,>=2.3.1\n",
      "  Downloading sentence_transformers-2.3.1-py3-none-any.whl (132 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m132.8/132.8 kB\u001b[0m \u001b[31m258.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: pyyaml in /opt/app-root/lib/python3.9/site-packages (from peft==0.6.0->caikit-nlp==0.4.9.dev2+gc12cb82) (6.0.1)\n",
      "Requirement already satisfied: psutil in /opt/app-root/lib/python3.9/site-packages (from peft==0.6.0->caikit-nlp==0.4.9.dev2+gc12cb82) (5.9.8)\n",
      "Requirement already satisfied: packaging>=20.0 in /opt/app-root/lib/python3.9/site-packages (from peft==0.6.0->caikit-nlp==0.4.9.dev2+gc12cb82) (23.2)\n",
      "Collecting safetensors\n",
      "  Downloading safetensors-0.4.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m334.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: grpcio<2.0,>=1.35.0 in /opt/app-root/lib/python3.9/site-packages (from caikit-tgis-backend<0.2.0,>=0.1.27->caikit-nlp==0.4.9.dev2+gc12cb82) (1.62.0)\n",
      "Requirement already satisfied: requests<3,>=2.28.2 in /opt/app-root/lib/python3.9/site-packages (from caikit-tgis-backend<0.2.0,>=0.1.27->caikit-nlp==0.4.9.dev2+gc12cb82) (2.31.0)\n",
      "Collecting alchemy-logging<2.0.0,>=1.3.2\n",
      "  Downloading alchemy_logging-1.3.2-py3-none-any.whl (18 kB)\n",
      "Collecting semver<4.0,>=2.13.0\n",
      "  Downloading semver-3.0.2-py3-none-any.whl (17 kB)\n",
      "Collecting alchemy-config<2.0.0,>=1.1.1\n",
      "  Downloading alchemy_config-1.1.3-py3-none-any.whl (7.3 kB)\n",
      "Requirement already satisfied: werkzeug<4.0.0,>=2.3.7 in /opt/app-root/lib/python3.9/site-packages (from caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (3.0.1)\n",
      "Collecting anytree<3.0,>=2.7.0\n",
      "  Downloading anytree-2.12.1-py3-none-any.whl (44 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.9/44.9 kB\u001b[0m \u001b[31m227.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting py-to-proto!=0.2.1,<0.6.0,>=0.5.0\n",
      "  Downloading py_to_proto-0.5.2-py39-none-any.whl (32 kB)\n",
      "Requirement already satisfied: importlib-metadata<8.0.0,>=6.8.0 in /opt/app-root/lib/python3.9/site-packages (from caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (7.0.1)\n",
      "Collecting munch<5.0,>=2.5.0\n",
      "  Downloading munch-4.0.0-py2.py3-none-any.whl (9.9 kB)\n",
      "Requirement already satisfied: protobuf<6,>=3.19.0 in /opt/app-root/lib/python3.9/site-packages (from caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (3.20.2)\n",
      "Requirement already satisfied: six<2.0.0,>=1.16.0 in /opt/app-root/lib/python3.9/site-packages (from caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (1.16.0)\n",
      "Collecting ijson<3.3.0,>=3.1.4\n",
      "  Downloading ijson-3.2.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (111 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m111.1/111.1 kB\u001b[0m \u001b[31m291.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting docstring-parser<0.17.0,>=0.14.1\n",
      "  Downloading docstring_parser-0.16-py3-none-any.whl (36 kB)\n",
      "Collecting py-grpc-prometheus<0.9,>=0.7.0\n",
      "  Downloading py_grpc_prometheus-0.8.0-py3-none-any.whl (12 kB)\n",
      "Collecting grpcio-health-checking<2.0,>=1.35.0\n",
      "  Downloading grpcio_health_checking-1.62.2-py3-none-any.whl (18 kB)\n",
      "Collecting grpcio-reflection<2.0,>=1.35.0\n",
      "  Downloading grpcio_reflection-1.62.2-py3-none-any.whl (22 kB)\n",
      "Requirement already satisfied: prometheus-client<1.0,>=0.12.0 in /opt/app-root/lib/python3.9/site-packages (from caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (0.20.0)\n",
      "Collecting sse-starlette<3,>=1.6.1\n",
      "  Downloading sse_starlette-2.1.0-py3-none-any.whl (9.2 kB)\n",
      "Collecting fastapi[all]<1,>=0.100\n",
      "  Downloading fastapi-0.110.2-py3-none-any.whl (91 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.9/91.9 kB\u001b[0m \u001b[31m290.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: pyarrow>=12.0.0 in /opt/app-root/lib/python3.9/site-packages (from datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (15.0.0)\n",
      "Requirement already satisfied: filelock in /opt/app-root/lib/python3.9/site-packages (from datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (3.13.1)\n",
      "Collecting xxhash\n",
      "  Downloading xxhash-3.4.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (193 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m193.8/193.8 kB\u001b[0m \u001b[31m304.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting multiprocess\n",
      "  Downloading multiprocess-0.70.16-py39-none-any.whl (133 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.4/133.4 kB\u001b[0m \u001b[31m270.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting pyarrow-hotfix\n",
      "  Downloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n",
      "Requirement already satisfied: fsspec[http]<=2024.3.1,>=2023.1.0 in /opt/app-root/lib/python3.9/site-packages (from datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (2024.2.0)\n",
      "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /opt/app-root/lib/python3.9/site-packages (from datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (0.3.8)\n",
      "Requirement already satisfied: aiohttp in /opt/app-root/lib/python3.9/site-packages (from datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (3.9.3)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/app-root/lib/python3.9/site-packages (from huggingface-hub->caikit-nlp==0.4.9.dev2+gc12cb82) (4.10.0)\n",
      "Requirement already satisfied: python-dateutil>=2.8.1 in /opt/app-root/lib/python3.9/site-packages (from pandas>=1.5.0->caikit-nlp==0.4.9.dev2+gc12cb82) (2.9.0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /opt/app-root/lib/python3.9/site-packages (from pandas>=1.5.0->caikit-nlp==0.4.9.dev2+gc12cb82) (2024.1)\n",
      "Requirement already satisfied: joblib>=1.1.1 in /opt/app-root/lib/python3.9/site-packages (from scikit-learn>=1.1->caikit-nlp==0.4.9.dev2+gc12cb82) (1.3.2)\n",
      "Requirement already satisfied: threadpoolctl>=2.0.0 in /opt/app-root/lib/python3.9/site-packages (from scikit-learn>=1.1->caikit-nlp==0.4.9.dev2+gc12cb82) (3.3.0)\n",
      "Requirement already satisfied: Pillow in /opt/app-root/lib/python3.9/site-packages (from sentence-transformers<2.4.0,>=2.3.1->caikit-nlp==0.4.9.dev2+gc12cb82) (10.2.0)\n",
      "Collecting sentencepiece\n",
      "  Downloading sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m322.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting nltk\n",
      "  Downloading nltk-3.8.1-py3-none-any.whl (1.5 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m334.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: triton==2.0.0 in /opt/app-root/lib/python3.9/site-packages (from torch>=2.0.1->caikit-nlp==0.4.9.dev2+gc12cb82) (2.0.0)\n",
      "Requirement already satisfied: networkx in /opt/app-root/lib/python3.9/site-packages (from torch>=2.0.1->caikit-nlp==0.4.9.dev2+gc12cb82) (3.2.1)\n",
      "Requirement already satisfied: jinja2 in /opt/app-root/lib/python3.9/site-packages (from torch>=2.0.1->caikit-nlp==0.4.9.dev2+gc12cb82) (3.1.3)\n",
      "Requirement already satisfied: sympy in /opt/app-root/lib/python3.9/site-packages (from torch>=2.0.1->caikit-nlp==0.4.9.dev2+gc12cb82) (1.12)\n",
      "Requirement already satisfied: cmake in /opt/app-root/lib/python3.9/site-packages (from triton==2.0.0->torch>=2.0.1->caikit-nlp==0.4.9.dev2+gc12cb82) (3.28.3)\n",
      "Requirement already satisfied: lit in /opt/app-root/lib/python3.9/site-packages (from triton==2.0.0->torch>=2.0.1->caikit-nlp==0.4.9.dev2+gc12cb82) (17.0.6)\n",
      "Collecting regex!=2019.12.17\n",
      "  Downloading regex-2024.4.16-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (773 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m773.4/773.4 kB\u001b[0m \u001b[31m342.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0,>=1.7.4 in /opt/app-root/lib/python3.9/site-packages (from fastapi[all]<1,>=0.100->caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (1.10.14)\n",
      "Collecting starlette<0.38.0,>=0.37.2\n",
      "  Downloading starlette-0.37.2-py3-none-any.whl (71 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m259.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting httpx>=0.23.0\n",
      "  Downloading httpx-0.27.0-py3-none-any.whl (75 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m278.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting uvicorn[standard]>=0.12.0\n",
      "  Downloading uvicorn-0.29.0-py3-none-any.whl (60 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m212.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting itsdangerous>=1.1.0\n",
      "  Downloading itsdangerous-2.2.0-py3-none-any.whl (16 kB)\n",
      "Collecting email-validator>=2.0.0\n",
      "  Downloading email_validator-2.1.1-py3-none-any.whl (30 kB)\n",
      "Collecting python-multipart>=0.0.7\n",
      "  Downloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n",
      "Collecting pydantic-extra-types>=2.0.0\n",
      "  Downloading pydantic_extra_types-2.7.0-py3-none-any.whl (25 kB)\n",
      "Collecting pydantic-settings>=2.0.0\n",
      "  Downloading pydantic_settings-2.2.1-py3-none-any.whl (13 kB)\n",
      "Collecting orjson>=3.2.1\n",
      "  Downloading orjson-3.10.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (140 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m140.9/140.9 kB\u001b[0m \u001b[31m280.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: ujson!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,>=4.0.1 in /opt/app-root/lib/python3.9/site-packages (from fastapi[all]<1,>=0.100->caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (5.9.0)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in /opt/app-root/lib/python3.9/site-packages (from aiohttp->datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (1.4.1)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in /opt/app-root/lib/python3.9/site-packages (from aiohttp->datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (6.0.5)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /opt/app-root/lib/python3.9/site-packages (from aiohttp->datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (23.2.0)\n",
      "Requirement already satisfied: async-timeout<5.0,>=4.0 in /opt/app-root/lib/python3.9/site-packages (from aiohttp->datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (4.0.3)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in /opt/app-root/lib/python3.9/site-packages (from aiohttp->datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (1.3.1)\n",
      "Requirement already satisfied: yarl<2.0,>=1.0 in /opt/app-root/lib/python3.9/site-packages (from aiohttp->datasets>=2.4.0->caikit-nlp==0.4.9.dev2+gc12cb82) (1.9.4)\n",
      "Collecting grpcio<2.0,>=1.35.0\n",
      "  Downloading grpcio-1.62.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.6 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.6/5.6 MB\u001b[0m \u001b[31m248.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting protobuf<6,>=3.19.0\n",
      "  Downloading protobuf-5.26.1-cp37-abi3-manylinux2014_x86_64.whl (302 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.8/302.8 kB\u001b[0m \u001b[31m258.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: zipp>=0.5 in /opt/app-root/lib/python3.9/site-packages (from importlib-metadata<8.0.0,>=6.8.0->caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (3.17.0)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /opt/app-root/lib/python3.9/site-packages (from jinja2->torch>=2.0.1->caikit-nlp==0.4.9.dev2+gc12cb82) (2.1.5)\n",
      "Requirement already satisfied: setuptools>=39.0.1 in /opt/app-root/lib/python3.9/site-packages (from py-grpc-prometheus<0.9,>=0.7.0->caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (68.1.2)\n",
      "  Downloading protobuf-4.25.3-cp37-abi3-manylinux2014_x86_64.whl (294 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m294.6/294.6 kB\u001b[0m \u001b[31m271.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: certifi>=2017.4.17 in /opt/app-root/lib/python3.9/site-packages (from requests<3,>=2.28.2->caikit-tgis-backend<0.2.0,>=0.1.27->caikit-nlp==0.4.9.dev2+gc12cb82) (2024.2.2)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/app-root/lib/python3.9/site-packages (from requests<3,>=2.28.2->caikit-tgis-backend<0.2.0,>=0.1.27->caikit-nlp==0.4.9.dev2+gc12cb82) (1.26.18)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /opt/app-root/lib/python3.9/site-packages (from requests<3,>=2.28.2->caikit-tgis-backend<0.2.0,>=0.1.27->caikit-nlp==0.4.9.dev2+gc12cb82) (3.6)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/app-root/lib/python3.9/site-packages (from requests<3,>=2.28.2->caikit-tgis-backend<0.2.0,>=0.1.27->caikit-nlp==0.4.9.dev2+gc12cb82) (3.3.2)\n",
      "Requirement already satisfied: anyio in /opt/app-root/lib/python3.9/site-packages (from sse-starlette<3,>=1.6.1->caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (4.3.0)\n",
      "Requirement already satisfied: click in /opt/app-root/lib/python3.9/site-packages (from nltk->sentence-transformers<2.4.0,>=2.3.1->caikit-nlp==0.4.9.dev2+gc12cb82) (8.1.7)\n",
      "Requirement already satisfied: mpmath>=0.19 in /opt/app-root/lib/python3.9/site-packages (from sympy->torch>=2.0.1->caikit-nlp==0.4.9.dev2+gc12cb82) (1.3.0)\n",
      "Requirement already satisfied: dnspython>=2.0.0 in /opt/app-root/lib/python3.9/site-packages (from email-validator>=2.0.0->fastapi[all]<1,>=0.100->caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (2.6.1)\n",
      "Collecting httpcore==1.*\n",
      "  Downloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m257.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: sniffio in /opt/app-root/lib/python3.9/site-packages (from httpx>=0.23.0->fastapi[all]<1,>=0.100->caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (1.3.1)\n",
      "Collecting h11<0.15,>=0.13\n",
      "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m244.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0,>=1.7.4\n",
      "  Downloading pydantic-2.7.1-py3-none-any.whl (409 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m409.3/409.3 kB\u001b[0m \u001b[31m274.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting annotated-types>=0.4.0\n",
      "  Downloading annotated_types-0.6.0-py3-none-any.whl (12 kB)\n",
      "Collecting pydantic-core==2.18.2\n",
      "  Downloading pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.1 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m218.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting python-dotenv>=0.21.0\n",
      "  Downloading python_dotenv-1.0.1-py3-none-any.whl (19 kB)\n",
      "Requirement already satisfied: exceptiongroup>=1.0.2 in /opt/app-root/lib/python3.9/site-packages (from anyio->sse-starlette<3,>=1.6.1->caikit[runtime-grpc,runtime-http]<0.27.0,>=0.26.17->caikit-nlp==0.4.9.dev2+gc12cb82) (1.2.0)\n",
      "Collecting watchfiles>=0.13\n",
      "  Downloading watchfiles-0.21.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m319.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting websockets>=10.4\n",
      "  Downloading websockets-12.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (130 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.0/130.0 kB\u001b[0m \u001b[31m283.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting httptools>=0.5.0\n",
      "  Downloading httptools-0.6.1-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (345 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m345.2/345.2 kB\u001b[0m \u001b[31m287.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting uvloop!=0.15.0,!=0.15.1,>=0.14.0\n",
      "  Downloading uvloop-0.19.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.5 MB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.5/3.5 MB\u001b[0m \u001b[31m232.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hBuilding wheels for collected packages: caikit-nlp\n",
      "  Building wheel for caikit-nlp (pyproject.toml) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for caikit-nlp: filename=caikit_nlp-0.4.9.dev2+gc12cb82-py3-none-any.whl size=105362 sha256=b53f539b8612cc617877ec0e663ee13a542a6753f3994459594083a1f9b9d17a\n",
      "  Stored in directory: /tmp/pip-ephem-wheel-cache-s8xp8dl9/wheels/c9/17/3b/9156973c813daca1cc62f7a708d527eef028b44cdbe9d52ea6\n",
      "Successfully built caikit-nlp\n",
      "Installing collected packages: sentencepiece, ijson, alchemy-logging, xxhash, websockets, uvloop, semver, safetensors, regex, python-multipart, python-dotenv, pydantic-core, pyarrow-hotfix, protobuf, orjson, munch, multiprocess, itsdangerous, httptools, h11, grpcio, email-validator, docstring-parser, anytree, annotated-types, alchemy-config, watchfiles, uvicorn, starlette, pydantic, py-to-proto, py-grpc-prometheus, nltk, huggingface-hub, httpcore, grpcio-reflection, grpcio-health-checking, tokenizers, sse-starlette, pydantic-settings, pydantic-extra-types, httpx, fastapi, caikit, transformers, datasets, caikit-tgis-backend, accelerate, sentence-transformers, peft, caikit-nlp\n",
      "  Attempting uninstall: protobuf\n",
      "    Found existing installation: protobuf 3.20.2\n",
      "    Uninstalling protobuf-3.20.2:\n",
      "      Successfully uninstalled protobuf-3.20.2\n",
      "  Attempting uninstall: grpcio\n",
      "    Found existing installation: grpcio 1.62.0\n",
      "    Uninstalling grpcio-1.62.0:\n",
      "      Successfully uninstalled grpcio-1.62.0\n",
      "  Attempting uninstall: docstring-parser\n",
      "    Found existing installation: docstring_parser 0.8.1\n",
      "    Uninstalling docstring_parser-0.8.1:\n",
      "      Successfully uninstalled docstring_parser-0.8.1\n",
      "  Attempting uninstall: pydantic\n",
      "    Found existing installation: pydantic 1.10.14\n",
      "    Uninstalling pydantic-1.10.14:\n",
      "      Successfully uninstalled pydantic-1.10.14\n",
      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
      "onnxconverter-common 1.14.0 requires protobuf==3.20.2, but you have protobuf 4.25.3 which is incompatible.\n",
      "mysql-connector-python 8.0.33 requires protobuf<=3.20.3,>=3.11.0, but you have protobuf 4.25.3 which is incompatible.\n",
      "kfp 1.8.22 requires protobuf<4,>=3.13.0, but you have protobuf 4.25.3 which is incompatible.\n",
      "kfp 1.8.22 requires pydantic<2,>=1.8.2, but you have pydantic 2.7.1 which is incompatible.\n",
      "kfp-pipeline-spec 0.1.16 requires protobuf<4,>=3.13.0, but you have protobuf 4.25.3 which is incompatible.\n",
      "codeflare-torchx 0.6.0.dev2 requires docstring-parser==0.8.1, but you have docstring-parser 0.16 which is incompatible.\n",
      "codeflare-sdk 0.14.1 requires pydantic<2, but you have pydantic 2.7.1 which is incompatible.\u001b[0m\u001b[31m\n",
      "\u001b[0mSuccessfully installed accelerate-0.29.3 alchemy-config-1.1.3 alchemy-logging-1.3.2 annotated-types-0.6.0 anytree-2.12.1 caikit-0.26.20 caikit-nlp-0.4.9.dev2+gc12cb82 caikit-tgis-backend-0.1.31 datasets-2.19.0 docstring-parser-0.16 email-validator-2.1.1 fastapi-0.110.2 grpcio-1.62.2 grpcio-health-checking-1.62.2 grpcio-reflection-1.62.2 h11-0.14.0 httpcore-1.0.5 httptools-0.6.1 httpx-0.27.0 huggingface-hub-0.22.2 ijson-3.2.3 itsdangerous-2.2.0 multiprocess-0.70.16 munch-4.0.0 nltk-3.8.1 orjson-3.10.1 peft-0.6.0 protobuf-4.25.3 py-grpc-prometheus-0.8.0 py-to-proto-0.5.2 pyarrow-hotfix-0.6 pydantic-2.7.1 pydantic-core-2.18.2 pydantic-extra-types-2.7.0 pydantic-settings-2.2.1 python-dotenv-1.0.1 python-multipart-0.0.9 regex-2024.4.16 safetensors-0.4.3 semver-3.0.2 sentence-transformers-2.3.1 sentencepiece-0.2.0 sse-starlette-2.1.0 starlette-0.37.2 tokenizers-0.19.1 transformers-4.40.1 uvicorn-0.29.0 uvloop-0.19.0 watchfiles-0.21.0 websockets-12.0 xxhash-3.4.1\n",
      "\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.2.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "!pip install ./caikit-nlp"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "579be6f8-fda5-451b-ac20-12f4c808b618",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "<function register_backend_type at 0x7f4aa20b7820> is still in the BETA phase and subject to change!\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import time\n",
    "import boto3\n",
    "import botocore\n",
    "\n",
    "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
    "from peft import PeftModel, PeftConfig\n",
    "import caikit_nlp"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fbf41b9e",
   "metadata": {},
   "source": [
    "### Load model from HuggingFace Hub and save locally"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "e9f7e5b0-5265-49f3-b0f7-cba6b6bf6e5b",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('../models/opt-350m_DETOXIFY_CAUSAL_LM/tokenizer_config.json',\n",
       " '../models/opt-350m_DETOXIFY_CAUSAL_LM/special_tokens_map.json',\n",
       " '../models/opt-350m_DETOXIFY_CAUSAL_LM/vocab.json',\n",
       " '../models/opt-350m_DETOXIFY_CAUSAL_LM/merges.txt',\n",
       " '../models/opt-350m_DETOXIFY_CAUSAL_LM/added_tokens.json',\n",
       " '../models/opt-350m_DETOXIFY_CAUSAL_LM/tokenizer.json')"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "output_dir = \"../models/opt-350m_DETOXIFY_CAUSAL_LM\"\n",
    "\n",
    "model = AutoModelForCausalLM.from_pretrained(\"facebook/opt-350m\")\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"facebook/opt-350m\")\n",
    "peft_model = PeftModel.from_pretrained(model, \"exyou/opt-350m_DETOXIFY_CAUSAL_LM\")\n",
    "peft_model = peft_model.merge_and_unload()\n",
    "\n",
    "peft_model.save_pretrained(output_dir)\n",
    "tokenizer.save_pretrained(output_dir)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "108e6ecf",
   "metadata": {},
   "source": [
    "### Convert model to Caikit format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "2b270421-e167-4fc4-9765-db7247357308",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Time to convert model: 9.06516 seconds\n"
     ]
    }
   ],
   "source": [
    "input_dir = \"../models/opt-350m_DETOXIFY_CAUSAL_LM\"\n",
    "\n",
    "output_dir = \"../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit\"\n",
    "\n",
    "start_time = time.time()\n",
    "model = caikit_nlp.text_generation.TextGeneration.bootstrap(input_dir)\n",
    "model.save(model_path=output_dir)\n",
    "end_time = time.time()\n",
    "print(f\"Time to convert model: {end_time - start_time:.5f} seconds\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8de1dad",
   "metadata": {},
   "source": [
    "### Upload Caikit model to S3 storage"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "5a5351e0-4ea3-4579-9d58-693e78b25f4d",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "aws_access_key_id = os.environ.get('AWS_ACCESS_KEY_ID')\n",
    "aws_secret_access_key = os.environ.get('AWS_SECRET_ACCESS_KEY')\n",
    "endpoint_url = os.environ.get('AWS_S3_ENDPOINT')\n",
    "region_name = os.environ.get('AWS_DEFAULT_REGION')\n",
    "bucket_name = os.environ.get('AWS_S3_BUCKET')\n",
    "\n",
    "session = boto3.session.Session(aws_access_key_id=aws_access_key_id,\n",
    "                                aws_secret_access_key=aws_secret_access_key)\n",
    "\n",
    "s3_resource = session.resource(\n",
    "    's3',\n",
    "    config=botocore.client.Config(signature_version='s3v4'),\n",
    "    endpoint_url=endpoint_url,\n",
    "    region_name=region_name)\n",
    "\n",
    "bucket = s3_resource.Bucket(bucket_name)\n",
    "\n",
    "\n",
    "def upload_directory_to_s3(local_directory, s3_prefix):\n",
    "    for root, dirs, files in os.walk(local_directory):\n",
    "        for filename in files:\n",
    "            file_path = os.path.join(root, filename)\n",
    "            relative_path = os.path.relpath(file_path, local_directory)\n",
    "            s3_key = os.path.join(s3_prefix, relative_path)\n",
    "            print(f\"{file_path} -> {s3_key}\")\n",
    "            bucket.upload_file(file_path, s3_key)\n",
    "\n",
    "def list_objects(prefix):\n",
    "    filter = bucket.objects.filter(Prefix=prefix)\n",
    "    for obj in filter.all():\n",
    "        print(obj.key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "09403e96-7970-4456-a480-faf153fe8bb7",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "../models/opt-350m_DETOXIFY_CAUSAL_LM/model.safetensors -> models/opt-350m_DETOXIFY_CAUSAL_LM/model.safetensors\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM/merges.txt -> models/opt-350m_DETOXIFY_CAUSAL_LM/merges.txt\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM/config.json -> models/opt-350m_DETOXIFY_CAUSAL_LM/config.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM/tokenizer.json -> models/opt-350m_DETOXIFY_CAUSAL_LM/tokenizer.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM/special_tokens_map.json -> models/opt-350m_DETOXIFY_CAUSAL_LM/special_tokens_map.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM/tokenizer_config.json -> models/opt-350m_DETOXIFY_CAUSAL_LM/tokenizer_config.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM/vocab.json -> models/opt-350m_DETOXIFY_CAUSAL_LM/vocab.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM/generation_config.json -> models/opt-350m_DETOXIFY_CAUSAL_LM/generation_config.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/config.yml -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/config.yml\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/model.safetensors -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/model.safetensors\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/merges.txt -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/merges.txt\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/config.json -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/config.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/tokenizer.json -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/tokenizer.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/special_tokens_map.json -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/special_tokens_map.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/tokenizer_config.json -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/tokenizer_config.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/vocab.json -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/vocab.json\n",
      "../models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/generation_config.json -> models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/generation_config.json\n"
     ]
    }
   ],
   "source": [
    "upload_directory_to_s3(\"../models\", \"models\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "6c478800-c961-49d2-a7cf-bc291c6eb175",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/config.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/generation_config.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/merges.txt\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/model.safetensors\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/special_tokens_map.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/tokenizer.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/tokenizer_config.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/artifacts/vocab.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM-caikit/config.yml\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM/config.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM/generation_config.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM/merges.txt\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM/model.safetensors\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM/special_tokens_map.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM/tokenizer.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM/tokenizer_config.json\n",
      "models/opt-350m_DETOXIFY_CAUSAL_LM/vocab.json\n"
     ]
    }
   ],
   "source": [
    "# sanity check\n",
    "list_objects(\"models\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}