notebooks/finetuning_notebook.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e19afbda-01d4-4208-a2d9-4597c5c1b61b",
   "metadata": {},
   "source": [
    "# Step1 getting started"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "56cbd667-f65e-42d7-85b0-a293edc8dec9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "============================ ROCm System Management Interface ============================\n",
      "====================================== Product Info ======================================\n",
      "GPU[0]\t\t: Card Series: \t\tInstinct MI210\n",
      "GPU[0]\t\t: Card Model: \t\t0x740f\n",
      "GPU[0]\t\t: Card Vendor: \t\tAdvanced Micro Devices, Inc. [AMD/ATI]\n",
      "GPU[0]\t\t: Card SKU: \t\tD67301V\n",
      "GPU[0]\t\t: Subsystem ID: \t0x0c34\n",
      "GPU[0]\t\t: Device Rev: \t\t0x02\n",
      "GPU[0]\t\t: Node ID: \t\t4\n",
      "GPU[0]\t\t: GUID: \t\t53592\n",
      "GPU[0]\t\t: GFX Version: \t\tgfx9010\n",
      "==========================================================================================\n",
      "================================== End of ROCm SMI Log ===================================\n"
     ]
    }
   ],
   "source": [
    "!rocm-smi --showproductname\n",
    "# sudo apt install libdrm-dev libsystemd-dev nvtop"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "555cfdef-04a6-4ebe-b7bd-24b4cf01830d",
   "metadata": {},
   "source": [
    "## Install Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7c6f30fb-5d5e-4533-b3bf-992222f41ae1",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting datasets\n",
      "  Downloading datasets-2.20.0-py3-none-any.whl.metadata (19 kB)\n",
      "Collecting transformers\n",
      "  Downloading transformers-4.43.1-py3-none-any.whl.metadata (43 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.7/43.7 kB\u001b[0m \u001b[31m17.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting peft\n",
      "  Downloading peft-0.11.1-py3-none-any.whl.metadata (13 kB)\n",
      "Collecting trl\n",
      "  Downloading trl-0.9.6-py3-none-any.whl.metadata (12 kB)\n",
      "Collecting accelerate\n",
      "  Downloading accelerate-0.33.0-py3-none-any.whl.metadata (18 kB)\n",
      "Requirement already satisfied: filelock in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from datasets) (3.14.0)\n",
      "Requirement already satisfied: numpy>=1.17 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from datasets) (1.20.3)\n",
      "Collecting pyarrow>=15.0.0 (from datasets)\n",
      "  Downloading pyarrow-17.0.0-cp39-cp39-manylinux_2_28_x86_64.whl.metadata (3.3 kB)\n",
      "Collecting pyarrow-hotfix (from datasets)\n",
      "  Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n",
      "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n",
      "  Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n",
      "Collecting pandas (from datasets)\n",
      "  Downloading pandas-2.2.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (19 kB)\n",
      "Requirement already satisfied: requests>=2.32.2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from datasets) (2.32.3)\n",
      "Requirement already satisfied: tqdm>=4.66.3 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from datasets) (4.66.4)\n",
      "Collecting xxhash (from datasets)\n",
      "  Downloading xxhash-3.4.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
      "Collecting multiprocess (from datasets)\n",
      "  Downloading multiprocess-0.70.16-py39-none-any.whl.metadata (7.2 kB)\n",
      "Collecting fsspec<=2024.5.0,>=2023.1.0 (from fsspec[http]<=2024.5.0,>=2023.1.0->datasets)\n",
      "  Downloading fsspec-2024.5.0-py3-none-any.whl.metadata (11 kB)\n",
      "Requirement already satisfied: aiohttp in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from datasets) (3.9.5)\n",
      "Collecting huggingface-hub>=0.21.2 (from datasets)\n",
      "  Downloading huggingface_hub-0.24.1-py3-none-any.whl.metadata (13 kB)\n",
      "Requirement already satisfied: packaging in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from datasets) (24.0)\n",
      "Requirement already satisfied: pyyaml>=5.1 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from datasets) (6.0.1)\n",
      "Collecting regex!=2019.12.17 (from transformers)\n",
      "  Downloading regex-2024.5.15-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m16.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting tokenizers<0.20,>=0.19 (from transformers)\n",
      "  Downloading tokenizers-0.19.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
      "Collecting safetensors>=0.4.1 (from transformers)\n",
      "  Downloading safetensors-0.4.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n",
      "Requirement already satisfied: psutil in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from peft) (5.9.8)\n",
      "Requirement already satisfied: torch>=1.13.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from peft) (2.0.1+git5b5a729)\n",
      "Collecting tyro>=0.5.11 (from trl)\n",
      "  Downloading tyro-0.8.5-py3-none-any.whl.metadata (8.2 kB)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from aiohttp->datasets) (1.3.1)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from aiohttp->datasets) (23.2.0)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from aiohttp->datasets) (1.4.1)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from aiohttp->datasets) (6.0.5)\n",
      "Requirement already satisfied: yarl<2.0,>=1.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from aiohttp->datasets) (1.9.4)\n",
      "Requirement already satisfied: async-timeout<5.0,>=4.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from aiohttp->datasets) (4.0.3)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from huggingface-hub>=0.21.2->datasets) (4.12.1)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from requests>=2.32.2->datasets) (3.3.2)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from requests>=2.32.2->datasets) (3.7)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from requests>=2.32.2->datasets) (1.26.18)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from requests>=2.32.2->datasets) (2024.6.2)\n",
      "Requirement already satisfied: sympy in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch>=1.13.0->peft) (1.12.1)\n",
      "Requirement already satisfied: networkx in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch>=1.13.0->peft) (2.6.3)\n",
      "Requirement already satisfied: jinja2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages/jinja2-3.1.4-py3.9.egg (from torch>=1.13.0->peft) (3.1.4)\n",
      "Requirement already satisfied: pytorch-triton-rocm<2.1,>=2.0.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages/pytorch_triton_rocm-2.0.2-py3.9-linux-x86_64.egg (from torch>=1.13.0->peft) (2.0.2)\n",
      "Collecting docstring-parser>=0.16 (from tyro>=0.5.11->trl)\n",
      "  Downloading docstring_parser-0.16-py3-none-any.whl.metadata (3.0 kB)\n",
      "Collecting rich>=11.1.0 (from tyro>=0.5.11->trl)\n",
      "  Downloading rich-13.7.1-py3-none-any.whl.metadata (18 kB)\n",
      "Collecting shtab>=1.5.6 (from tyro>=0.5.11->trl)\n",
      "  Downloading shtab-1.7.1-py3-none-any.whl.metadata (7.3 kB)\n",
      "Collecting eval-type-backport>=0.1.3 (from tyro>=0.5.11->trl)\n",
      "  Downloading eval_type_backport-0.2.0-py3-none-any.whl.metadata (2.2 kB)\n",
      "Collecting numpy>=1.17 (from datasets)\n",
      "  Downloading numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (61 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.0/61.0 kB\u001b[0m \u001b[31m22.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pandas->datasets) (2.9.0.post0)\n",
      "Collecting pytz>=2020.1 (from pandas->datasets)\n",
      "  Downloading pytz-2024.1-py2.py3-none-any.whl.metadata (22 kB)\n",
      "Collecting tzdata>=2022.7 (from pandas->datasets)\n",
      "  Downloading tzdata-2024.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
      "Requirement already satisfied: six>=1.5 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n",
      "Requirement already satisfied: cmake in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytorch-triton-rocm<2.1,>=2.0.0->torch>=1.13.0->peft) (3.29.3)\n",
      "Requirement already satisfied: lit in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytorch-triton-rocm<2.1,>=2.0.0->torch>=1.13.0->peft) (18.1.6)\n",
      "Collecting markdown-it-py>=2.2.0 (from rich>=11.1.0->tyro>=0.5.11->trl)\n",
      "  Downloading markdown_it_py-3.0.0-py3-none-any.whl.metadata (6.9 kB)\n",
      "Collecting pygments<3.0.0,>=2.13.0 (from rich>=11.1.0->tyro>=0.5.11->trl)\n",
      "  Downloading pygments-2.18.0-py3-none-any.whl.metadata (2.5 kB)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from jinja2->torch>=1.13.0->peft) (2.1.5)\n",
      "Requirement already satisfied: mpmath<1.4.0,>=1.1.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from sympy->torch>=1.13.0->peft) (1.3.0)\n",
      "Collecting mdurl~=0.1 (from markdown-it-py>=2.2.0->rich>=11.1.0->tyro>=0.5.11->trl)\n",
      "  Downloading mdurl-0.1.2-py3-none-any.whl.metadata (1.6 kB)\n",
      "Downloading datasets-2.20.0-py3-none-any.whl (547 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m547.8/547.8 kB\u001b[0m \u001b[31m72.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading transformers-4.43.1-py3-none-any.whl (9.4 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.4/9.4 MB\u001b[0m \u001b[31m91.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hDownloading peft-0.11.1-py3-none-any.whl (251 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m251.6/251.6 kB\u001b[0m \u001b[31m74.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading trl-0.9.6-py3-none-any.whl (245 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m245.8/245.8 kB\u001b[0m \u001b[31m77.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading accelerate-0.33.0-py3-none-any.whl (315 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m315.1/315.1 kB\u001b[0m \u001b[31m88.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading dill-0.3.8-py3-none-any.whl (116 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m46.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading fsspec-2024.5.0-py3-none-any.whl (316 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m316.1/316.1 kB\u001b[0m \u001b[31m86.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading huggingface_hub-0.24.1-py3-none-any.whl (417 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m417.2/417.2 kB\u001b[0m \u001b[31m95.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading pyarrow-17.0.0-cp39-cp39-manylinux_2_28_x86_64.whl (39.9 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m39.9/39.9 MB\u001b[0m \u001b[31m55.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading regex-2024.5.15-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (774 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m774.6/774.6 kB\u001b[0m \u001b[31m94.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading 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[31m86.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading 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[31m91.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n",
      "\u001b[?25hDownloading tyro-0.8.5-py3-none-any.whl (103 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m103.4/103.4 kB\u001b[0m \u001b[31m36.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading 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[31m48.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading pandas-2.2.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.1 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.1/13.1 MB\u001b[0m \u001b[31m85.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.2/18.2 MB\u001b[0m \u001b[31m77.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\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[31m63.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading docstring_parser-0.16-py3-none-any.whl (36 kB)\n",
      "Downloading eval_type_backport-0.2.0-py3-none-any.whl (5.9 kB)\n",
      "Downloading pytz-2024.1-py2.py3-none-any.whl (505 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m505.5/505.5 kB\u001b[0m \u001b[31m89.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading rich-13.7.1-py3-none-any.whl (240 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m240.7/240.7 kB\u001b[0m \u001b[31m68.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading shtab-1.7.1-py3-none-any.whl (14 kB)\n",
      "Downloading tzdata-2024.1-py2.py3-none-any.whl (345 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m345.4/345.4 kB\u001b[0m \u001b[31m89.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading markdown_it_py-3.0.0-py3-none-any.whl (87 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.5/87.5 kB\u001b[0m \u001b[31m37.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading pygments-2.18.0-py3-none-any.whl (1.2 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m90.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading mdurl-0.1.2-py3-none-any.whl (10.0 kB)\n",
      "Installing collected packages: pytz, xxhash, tzdata, shtab, safetensors, regex, pygments, pyarrow-hotfix, numpy, mdurl, fsspec, eval-type-backport, docstring-parser, dill, pyarrow, pandas, multiprocess, markdown-it-py, huggingface-hub, tokenizers, rich, tyro, transformers, datasets, accelerate, trl, peft\n",
      "  Attempting uninstall: pygments\n",
      "    Found existing installation: Pygments 2.12.0\n",
      "    Uninstalling Pygments-2.12.0:\n",
      "      Successfully uninstalled Pygments-2.12.0\n",
      "  Attempting uninstall: numpy\n",
      "    Found existing installation: numpy 1.20.3\n",
      "    Uninstalling numpy-1.20.3:\n",
      "      Successfully uninstalled numpy-1.20.3\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",
      "numba 0.54.1 requires numpy<1.21,>=1.17, but you have numpy 1.26.4 which is incompatible.\n",
      "scipy 1.6.3 requires numpy<1.23.0,>=1.16.5, but you have numpy 1.26.4 which is incompatible.\u001b[0m\u001b[31m\n",
      "\u001b[0mSuccessfully installed accelerate-0.33.0 datasets-2.20.0 dill-0.3.8 docstring-parser-0.16 eval-type-backport-0.2.0 fsspec-2024.5.0 huggingface-hub-0.24.1 markdown-it-py-3.0.0 mdurl-0.1.2 multiprocess-0.70.16 numpy-1.26.4 pandas-2.2.2 peft-0.11.1 pyarrow-17.0.0 pyarrow-hotfix-0.6 pygments-2.18.0 pytz-2024.1 regex-2024.5.15 rich-13.7.1 safetensors-0.4.3 shtab-1.7.1 tokenizers-0.19.1 transformers-4.43.1 trl-0.9.6 tyro-0.8.5 tzdata-2024.1 xxhash-3.4.1\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.\u001b[0m\u001b[33m\n",
      "\u001b[0m"
     ]
    }
   ],
   "source": [
    "!pip install datasets transformers peft trl accelerate"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fac33e40-9de6-40ff-9bdb-00b73bbccaaa",
   "metadata": {},
   "source": [
    "## Install bits and bytes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5948a4e1-7c3e-48f0-9b57-d5ce35b98765",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "fatal: destination path 'bitsandbytes' already exists and is not an empty directory.\n",
      "/home/aac/bitsandbytes\n",
      "fatal: detected dubious ownership in repository at '/home/aac/bitsandbytes'\n",
      "To add an exception for this directory, call:\n",
      "\n",
      "\tgit config --global --add safe.directory /home/aac/bitsandbytes\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/IPython/core/magics/osm.py:417: UserWarning: using dhist requires you to install the `pickleshare` library.\n",
      "  self.shell.db['dhist'] = compress_dhist(dhist)[-100:]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: setuptools>=63 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from -r requirements-dev.txt (line 2)) (71.1.0)\n",
      "Requirement already satisfied: pytest~=8.2.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from -r requirements-dev.txt (line 3)) (8.2.2)\n",
      "Collecting einops~=0.8.0 (from -r requirements-dev.txt (line 4))\n",
      "  Downloading einops-0.8.0-py3-none-any.whl.metadata (12 kB)\n",
      "Requirement already satisfied: wheel~=0.43.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from -r requirements-dev.txt (line 5)) (0.43.0)\n",
      "Collecting lion-pytorch~=0.1.4 (from -r requirements-dev.txt (line 6))\n",
      "  Downloading lion_pytorch-0.1.4-py3-none-any.whl.metadata (618 bytes)\n",
      "Collecting scipy~=1.13.0 (from -r requirements-dev.txt (line 7))\n",
      "  Downloading scipy-1.13.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.6/60.6 kB\u001b[0m \u001b[31m25.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: pandas~=2.2.2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from -r requirements-dev.txt (line 8)) (2.2.2)\n",
      "Collecting matplotlib~=3.8.4 (from -r requirements-dev.txt (line 9))\n",
      "  Downloading matplotlib-3.8.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.8 kB)\n",
      "Requirement already satisfied: iniconfig in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytest~=8.2.0->-r requirements-dev.txt (line 3)) (2.0.0)\n",
      "Requirement already satisfied: packaging in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytest~=8.2.0->-r requirements-dev.txt (line 3)) (24.0)\n",
      "Requirement already satisfied: pluggy<2.0,>=1.5 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytest~=8.2.0->-r requirements-dev.txt (line 3)) (1.5.0)\n",
      "Requirement already satisfied: exceptiongroup>=1.0.0rc8 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytest~=8.2.0->-r requirements-dev.txt (line 3)) (1.2.1)\n",
      "Requirement already satisfied: tomli>=1 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytest~=8.2.0->-r requirements-dev.txt (line 3)) (2.0.1)\n",
      "Requirement already satisfied: torch>=1.6 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (2.0.1+git5b5a729)\n",
      "Requirement already satisfied: numpy<2.3,>=1.22.4 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from scipy~=1.13.0->-r requirements-dev.txt (line 7)) (1.26.4)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pandas~=2.2.2->-r requirements-dev.txt (line 8)) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pandas~=2.2.2->-r requirements-dev.txt (line 8)) (2024.1)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pandas~=2.2.2->-r requirements-dev.txt (line 8)) (2024.1)\n",
      "Collecting contourpy>=1.0.1 (from matplotlib~=3.8.4->-r requirements-dev.txt (line 9))\n",
      "  Downloading contourpy-1.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.8 kB)\n",
      "Collecting cycler>=0.10 (from matplotlib~=3.8.4->-r requirements-dev.txt (line 9))\n",
      "  Downloading cycler-0.12.1-py3-none-any.whl.metadata (3.8 kB)\n",
      "Collecting fonttools>=4.22.0 (from matplotlib~=3.8.4->-r requirements-dev.txt (line 9))\n",
      "  Downloading fonttools-4.53.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (162 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m162.6/162.6 kB\u001b[0m \u001b[31m55.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting kiwisolver>=1.3.1 (from matplotlib~=3.8.4->-r requirements-dev.txt (line 9))\n",
      "  Downloading kiwisolver-1.4.5-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl.metadata (6.4 kB)\n",
      "Requirement already satisfied: pillow>=8 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from matplotlib~=3.8.4->-r requirements-dev.txt (line 9)) (10.3.0)\n",
      "Collecting pyparsing>=2.3.1 (from matplotlib~=3.8.4->-r requirements-dev.txt (line 9))\n",
      "  Downloading pyparsing-3.1.2-py3-none-any.whl.metadata (5.1 kB)\n",
      "Collecting importlib-resources>=3.2.0 (from matplotlib~=3.8.4->-r requirements-dev.txt (line 9))\n",
      "  Downloading importlib_resources-6.4.0-py3-none-any.whl.metadata (3.9 kB)\n",
      "Requirement already satisfied: zipp>=3.1.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from importlib-resources>=3.2.0->matplotlib~=3.8.4->-r requirements-dev.txt (line 9)) (3.19.2)\n",
      "Requirement already satisfied: six>=1.5 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from python-dateutil>=2.8.2->pandas~=2.2.2->-r requirements-dev.txt (line 8)) (1.16.0)\n",
      "Requirement already satisfied: filelock in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (3.14.0)\n",
      "Requirement already satisfied: typing-extensions in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (4.12.1)\n",
      "Requirement already satisfied: sympy in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (1.12.1)\n",
      "Requirement already satisfied: networkx in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (2.6.3)\n",
      "Requirement already satisfied: jinja2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages/jinja2-3.1.4-py3.9.egg (from torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (3.1.4)\n",
      "Requirement already satisfied: pytorch-triton-rocm<2.1,>=2.0.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages/pytorch_triton_rocm-2.0.2-py3.9-linux-x86_64.egg (from torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (2.0.2)\n",
      "Requirement already satisfied: cmake in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytorch-triton-rocm<2.1,>=2.0.0->torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (3.29.3)\n",
      "Requirement already satisfied: lit in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytorch-triton-rocm<2.1,>=2.0.0->torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (18.1.6)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from jinja2->torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (2.1.5)\n",
      "Requirement already satisfied: mpmath<1.4.0,>=1.1.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from sympy->torch>=1.6->lion-pytorch~=0.1.4->-r requirements-dev.txt (line 6)) (1.3.0)\n",
      "Downloading einops-0.8.0-py3-none-any.whl (43 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.2/43.2 kB\u001b[0m \u001b[31m18.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading lion_pytorch-0.1.4-py3-none-any.whl (4.3 kB)\n",
      "Downloading scipy-1.13.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.6 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.6/38.6 MB\u001b[0m \u001b[31m57.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading matplotlib-3.8.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.6/11.6 MB\u001b[0m \u001b[31m87.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m0:01\u001b[0m\n",
      "\u001b[?25hDownloading contourpy-1.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (304 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m305.0/305.0 kB\u001b[0m \u001b[31m84.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading cycler-0.12.1-py3-none-any.whl (8.3 kB)\n",
      "Downloading fonttools-4.53.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.6 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.6/4.6 MB\u001b[0m \u001b[31m91.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hDownloading importlib_resources-6.4.0-py3-none-any.whl (38 kB)\n",
      "Downloading kiwisolver-1.4.5-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.6 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m89.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading pyparsing-3.1.2-py3-none-any.whl (103 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m103.2/103.2 kB\u001b[0m \u001b[31m39.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hInstalling collected packages: scipy, pyparsing, kiwisolver, importlib-resources, fonttools, einops, cycler, contourpy, matplotlib, lion-pytorch\n",
      "  Attempting uninstall: scipy\n",
      "    Found existing installation: scipy 1.6.3\n",
      "    Uninstalling scipy-1.6.3:\n",
      "      Successfully uninstalled scipy-1.6.3\n",
      "Successfully installed contourpy-1.2.1 cycler-0.12.1 einops-0.8.0 fonttools-4.53.1 importlib-resources-6.4.0 kiwisolver-1.4.5 lion-pytorch-0.1.4 matplotlib-3.8.4 pyparsing-3.1.2 scipy-1.13.1\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.\u001b[0m\u001b[33m\n",
      "\u001b[0m-- Configuring bitsandbytes (Backend: hip)\n",
      "-- NO_CUBLASLT := OFF\n",
      "-- HIP Compiler: /opt/rocm/llvm/bin/clang++\n",
      "-- HIP Targets: gfx900;gfx906;gfx908;gfx90a;gfx1030;gfx1100;gfx1101;gfx940;gfx941;gfx942\n",
      "\u001b[0mhipblas VERSION: 2.1.0\u001b[0m\n",
      "\u001b[0mhiprand VERSION: 2.10.16\u001b[0m\n",
      "\u001b[0mhipsparse VERSION: 3.0.1\u001b[0m\n",
      "-- Configuring done (0.4s)\n",
      "-- Generating done (0.0s)\n",
      "-- Build files have been written to: /home/aac/bitsandbytes\n",
      "[100%] Built target bitsandbytes\n",
      "Processing /home/aac/bitsandbytes\n",
      "  Installing build dependencies ... \u001b[?25ldone\n",
      "\u001b[?25h  Getting requirements to build wheel ... \u001b[?25ldone\n",
      "\u001b[?25h  Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
      "\u001b[?25hRequirement already satisfied: torch in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from bitsandbytes==0.43.2.dev0) (2.0.1+git5b5a729)\n",
      "Requirement already satisfied: numpy in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from bitsandbytes==0.43.2.dev0) (1.26.4)\n",
      "Requirement already satisfied: filelock in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch->bitsandbytes==0.43.2.dev0) (3.14.0)\n",
      "Requirement already satisfied: typing-extensions in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch->bitsandbytes==0.43.2.dev0) (4.12.1)\n",
      "Requirement already satisfied: sympy in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch->bitsandbytes==0.43.2.dev0) (1.12.1)\n",
      "Requirement already satisfied: networkx in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from torch->bitsandbytes==0.43.2.dev0) (2.6.3)\n",
      "Requirement already satisfied: jinja2 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages/jinja2-3.1.4-py3.9.egg (from torch->bitsandbytes==0.43.2.dev0) (3.1.4)\n",
      "Requirement already satisfied: pytorch-triton-rocm<2.1,>=2.0.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages/pytorch_triton_rocm-2.0.2-py3.9-linux-x86_64.egg (from torch->bitsandbytes==0.43.2.dev0) (2.0.2)\n",
      "Requirement already satisfied: cmake in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytorch-triton-rocm<2.1,>=2.0.0->torch->bitsandbytes==0.43.2.dev0) (3.29.3)\n",
      "Requirement already satisfied: lit in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from pytorch-triton-rocm<2.1,>=2.0.0->torch->bitsandbytes==0.43.2.dev0) (18.1.6)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from jinja2->torch->bitsandbytes==0.43.2.dev0) (2.1.5)\n",
      "Requirement already satisfied: mpmath<1.4.0,>=1.1.0 in /opt/conda/envs/py_3.9/lib/python3.9/site-packages (from sympy->torch->bitsandbytes==0.43.2.dev0) (1.3.0)\n",
      "Building wheels for collected packages: bitsandbytes\n",
      "  Building wheel for bitsandbytes (pyproject.toml) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for bitsandbytes: filename=bitsandbytes-0.43.2.dev0-cp39-cp39-linux_x86_64.whl size=2711418 sha256=812b19999c4a64804a764f8711b8d6c1ea2163880442d81b21706c9cfe0765a4\n",
      "  Stored in directory: /tmp/pip-ephem-wheel-cache-jj9e2w7x/wheels/56/a7/0c/3a738b785a0c8c21d509c24749af3e0529f1ed58a77a5fa50a\n",
      "Successfully built bitsandbytes\n",
      "Installing collected packages: bitsandbytes\n",
      "Successfully installed bitsandbytes-0.43.2.dev0\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable.It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.\u001b[0m\u001b[33m\n",
      "\u001b[0m/home/aac\n"
     ]
    }
   ],
   "source": [
    "!git clone --recurse https://github.com/ROCm/bitsandbytes\n",
    "!git config --global --add safe.directory /home/aac\n",
    "%cd /home/aac/bitsandbytes\n",
    "!git checkout rocm_enabled\n",
    "!pip install -r requirements-dev.txt\n",
    "!cmake -DCOMPUTE_BACKEND=hip -S . #Use -DBNB_ROCM_ARCH=\"gfx90a;gfx942\" to target specific gpu arch\n",
    "!make\n",
    "!pip install .\n",
    "%cd /home/aac/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ae7a7eac-36c0-4a37-9047-e964a7ed0c24",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#!pip install datasets transformers peft trl accelerate"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5b78258a-3043-43a4-baa6-7b8b256c026c",
   "metadata": {},
   "source": [
    "## Import the required packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "00bc6012-7f26-4fa8-993c-2ac94bd48b3b",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "from datasets import load_dataset, load_from_disk\n",
    "from transformers import (\n",
    "    AutoModelForCausalLM,\n",
    "    AutoTokenizer,\n",
    "    BitsAndBytesConfig,\n",
    "    TrainingArguments,\n",
    "    pipeline\n",
    ")\n",
    "from peft import LoraConfig\n",
    "from trl import SFTTrainer"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b69e39cc-0c64-4b87-b231-b499f8ba1cbc",
   "metadata": {},
   "source": [
    "# Step 2: Configuring the model and data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "87662be1-1745-412e-bade-c7314a551de5",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Loading checkpoint shards: 100%|██████████| 7/7 [04:36<00:00, 39.48s/it]\n"
     ]
    }
   ],
   "source": [
    "\n",
    "import os\n",
    "\n",
    "# Model and tokenizer names\n",
    "base_model_name = \"Meta-Llama-3-8B-Instruct\" # \"meta-llama/Meta-Llama-3-8B-Instruct\"\n",
    "new_model_name = \"llama-3-8b-gmap-recomm\" #You can give your own name for fine tuned model\n",
    "\n",
    "# Tokenizer\n",
    "llama_tokenizer = AutoTokenizer.from_pretrained('meta-llama/Meta-Llama-3-8B-Instruct', trust_remote_code=True)\n",
    "llama_tokenizer.pad_token = llama_tokenizer.eos_token\n",
    "llama_tokenizer.padding_side = \"right\"\n",
    "\n",
    "# Model\n",
    "base_model = AutoModelForCausalLM.from_pretrained(\n",
    "    base_model_name,\n",
    "    device_map=\"auto\",\n",
    "    #torch_dtype=torch.float16,\n",
    "    \n",
    ")\n",
    "base_model.config.use_cache = False\n",
    "base_model.config.pretraining_tp = 1\n",
    "# base_model.save_pretrained('Meta-Llama-3-8B-Instruct')\n",
    "# llama_tokenizer.save_pretrained('Meta-Llama-3-8B-Instruct')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e549edaa-90c9-420e-8db9-d6c68022a986",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Downloading readme: 100%|██████████| 1.02k/1.02k [00:00<00:00, 14.3MB/s]\n",
      "Downloading data: 100%|██████████| 967k/967k [00:00<00:00, 2.57MB/s]\n",
      "Generating train split: 100%|██████████| 1000/1000 [00:00<00:00, 139572.86 examples/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1000, 1)\n",
      "{'text': '<s>[INST] Me gradué hace poco de la carrera de medicina ¿Me podrías aconsejar para conseguir rápidamente un puesto de trabajo? [/INST] Esto vale tanto para médicos como para cualquier otra profesión tras finalizar los estudios aniversarios y mi consejo sería preguntar a cuántas personas haya conocido mejor. En este caso, mi primera opción sería hablar con otros profesionales médicos, echar currículos en hospitales y cualquier centro de salud. En paralelo, trabajaría por mejorar mi marca personal como médico mediante un blog o formas digitales de comunicación como los vídeos. Y, para mejorar las posibilidades de encontrar trabajo, también participaría en congresos y encuentros para conseguir más contactos. Y, además de todo lo anterior, seguiría estudiando para presentarme a las oposiciones y ejercer la medicina en el sector público de mi país. </s>'}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "# Data set\n",
    "data_name = \"mlabonne/guanaco-llama2-1k\"\n",
    "training_data = load_dataset(data_name, split=\"train\")\n",
    "# check the data\n",
    "print(training_data.shape)\n",
    "# #11 is a QA sample in English\n",
    "print(training_data[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "3aaf5542-eda1-42d8-af04-38b4cd82617e",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Map: 100%|██████████| 20565/20565 [00:00<00:00, 44917.84 examples/s]\n"
     ]
    }
   ],
   "source": [
    "def preprocess_function(examples):\n",
    "    # Combine relevant fields into a single text field\n",
    "    texts = [\n",
    "        f\"Question: {q}\\nContext: {c}\\nCOTAnswer: {a}\"\n",
    "        for q, c, a in zip(examples['question'], examples['oracle_context'], examples['cot_answer'])\n",
    "    ]\n",
    "    \n",
    "    # Return a dictionary with the new 'text' field\n",
    "    return {\"text\": texts}\n",
    "\n",
    "def prepare_dataset_for_sft(dataset_path):\n",
    "    # Load the dataset\n",
    "    dataset = load_from_disk(dataset_path)\n",
    "    \n",
    "    # Preprocess the dataset\n",
    "    preprocessed_dataset = dataset.map(\n",
    "        preprocess_function,\n",
    "        batched=True,\n",
    "        remove_columns=dataset.column_names  # Remove original columns\n",
    "    )\n",
    "    \n",
    "    # Set the format to PyTorch tensors\n",
    "    preprocessed_dataset.set_format(type=\"torch\")\n",
    "    return preprocessed_dataset\n",
    "\n",
    "training_data = prepare_dataset_for_sft(\n",
    "    dataset_path=\"datasets/arrow_dataset\",\n",
    ")\n",
    "#training_data.save_to_disk('datasets/dataset_preprocessed')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e2b9d446-7793-4a0b-89e8-ec9054c57702",
   "metadata": {},
   "outputs": [],
   "source": [
    "#training_data = load_from_disk('datasets/dataset_preprocessed/')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "85846b2a-ca19-4577-afa0-20607df56f0d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'text': 'Question: How would you rate the overall quality of service provided by Majestic Security based on user reviews?\\nContext: {\"name\": \"Majestic Security\", \"address\": \"Majestic Security, 3128 Lexington Park Dr, Elkhart, IN 46514\", \"gmap_id\": \"0x8816c4b2fb8fb6a1:0x80451636e10ca83f\", \"description\": null, \"latitude\": 41.6899261, \"longitude\": -86.02416989999999, \"category\": [\"Security guard service\", \"Business to business service\", \"Public safety office\", \"Security service\", \"Training centre\", \"Training school\", \"Transportation escort service\"], \"avg_rating\": 4.3, \"num_of_reviews\": 48, \"price\": null, \"hours\": [[\"Thursday\", \"9AM\\\\u20135PM\"], [\"Friday\", \"9AM\\\\u20135PM\"], [\"Saturday\", \"Closed\"], [\"Sunday\", \"Closed\"], [\"Monday\", \"9AM\\\\u20135PM\"], [\"Tuesday\", \"9AM\\\\u20135PM\"], [\"Wednesday\", \"9AM\\\\u20135PM\"]], \"MISC\": null, \"state\": \"Open \\\\u22c5 Closes 5PM\", \"relative_results\": [\"0x8816e8092cc37eff:0xa138075153591bc7\", \"0x8816ce61cc404e23:0x71a5e9e0898036a4\", \"0x8816e9eb8afbc539:0x7d7ee677df3fafa3\", \"0x8816cd46eed45c35:0x7d80db2d3b489fc3\", \"0x8816ebe5c65cf3ad:0xe8dede77091f4ecf\"], \"url\": \"https://www.google.com/maps/place//data=!4m2!3m1!1s0x8816c4b2fb8fb6a1:0x80451636e10ca83f?authuser=-1&hl=en&gl=us\"}\\nCOTAnswer: To rate the overall quality of service provided by Majestic Security based on user reviews, I can analyze the average rating (4.3) and the number of reviews (48). This suggests that a significant portion of customers have had positive experiences with the company.\\n\\n##begin_quote##The high average rating indicates a strong level of satisfaction among users.##end_quote##\\n\\nTaking this into account, I would rate the overall quality of service provided by Majestic Security as:\\n\\n<ANSWER>: Excellent'}\n"
     ]
    }
   ],
   "source": [
    "print(training_data[3])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a4e60c79-ef64-472d-803e-f60c84678087",
   "metadata": {},
   "source": [
    "# Step 3: Start fine-tuning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "af771954-905a-43af-9ea4-960a58915663",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Training Params\n",
    "train_params = TrainingArguments(\n",
    "    output_dir=\"./results_modified_v2\",\n",
    "    num_train_epochs=2,\n",
    "    per_device_train_batch_size=1,\n",
    "    gradient_accumulation_steps=1,\n",
    "    #optim=\"paged_adamw_32bit\",\n",
    "    save_steps=3000,\n",
    "    logging_steps=50,\n",
    "    learning_rate=4e-5,\n",
    "    weight_decay=0.001,\n",
    "    fp16=False,\n",
    "    bf16=False,\n",
    "    max_grad_norm=0.3,\n",
    "    max_steps=-1,\n",
    "    warmup_ratio=0.03,\n",
    "    group_by_length=True,\n",
    "    lr_scheduler_type=\"constant\",\n",
    "    report_to=\"tensorboard\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "31d4520f-04e3-4c2e-8c13-f3fd8d89dfea",
   "metadata": {},
   "source": [
    "Training with LoRA configuration\n",
    "Now you can integrate LoRA into the base model and assess its additional parameters. LoRA essentially adds pairs of rank-decomposition weight matrices (called update matrices) to existing weights, and only trains the newly added weights."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "fd52f9ff-6727-4657-9c3e-547d60c1e3f6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "trainable params: 3,407,872 || all params: 8,033,669,120 || trainable%: 0.0424\n"
     ]
    }
   ],
   "source": [
    "from peft import get_peft_model\n",
    "# LoRA Config\n",
    "peft_parameters = LoraConfig(\n",
    "    lora_alpha=8,\n",
    "    lora_dropout=0.1,\n",
    "    r=8,\n",
    "    target_modules= ['q_proj', 'v_proj'],\n",
    "    bias=\"none\",\n",
    "    task_type=\"CAUSAL_LM\"\n",
    ")\n",
    "model = get_peft_model(base_model, peft_parameters)\n",
    "model.print_trainable_parameters()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "59c4ad53-3ee7-4005-a158-e4e6f7722289",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/huggingface_hub/utils/_deprecation.py:100: FutureWarning: Deprecated argument(s) used in '__init__': dataset_text_field. Will not be supported from version '1.0.0'.\n",
      "\n",
      "Deprecated positional argument(s) used in SFTTrainer, please use the SFTConfig to set these arguments instead.\n",
      "  warnings.warn(message, FutureWarning)\n",
      "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/trl/trainer/sft_trainer.py:289: UserWarning: You didn't pass a `max_seq_length` argument to the SFTTrainer, this will default to 1024\n",
      "  warnings.warn(\n",
      "/opt/conda/envs/py_3.9/lib/python3.9/site-packages/trl/trainer/sft_trainer.py:318: UserWarning: You passed a `dataset_text_field` argument to the SFTTrainer, the value you passed will override the one in the `SFTConfig`.\n",
      "  warnings.warn(\n",
      "Map:   0%|          | 0/20565 [00:00<?, ? examples/s]Asking to truncate to max_length but no maximum length is provided and the model has no predefined maximum length. Default to no truncation.\n",
      "Map: 100%|██████████| 20565/20565 [00:04<00:00, 4763.92 examples/s]\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      \n",
       "      <progress value='8245' max='41130' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      [ 8245/41130 1:26:58 < 5:46:58, 1.58 it/s, Epoch 0.40/2]\n",
       "    </div>\n",
       "    <table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       " <tr style=\"text-align: left;\">\n",
       "      <th>Step</th>\n",
       "      <th>Training Loss</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>50</td>\n",
       "      <td>2.077800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>100</td>\n",
       "      <td>1.732400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>150</td>\n",
       "      <td>1.482600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>200</td>\n",
       "      <td>1.328000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>250</td>\n",
       "      <td>1.348500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>300</td>\n",
       "      <td>1.311300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>350</td>\n",
       "      <td>1.336100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>400</td>\n",
       "      <td>1.314600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>450</td>\n",
       "      <td>1.235500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>500</td>\n",
       "      <td>1.183600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>550</td>\n",
       "      <td>1.210700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>600</td>\n",
       "      <td>1.167500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>650</td>\n",
       "      <td>1.226700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>700</td>\n",
       "      <td>1.188500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>750</td>\n",
       "      <td>1.211600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>800</td>\n",
       "      <td>1.221700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>850</td>\n",
       "      <td>1.169900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>900</td>\n",
       "      <td>1.212000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>950</td>\n",
       "      <td>1.204000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1000</td>\n",
       "      <td>1.202000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1050</td>\n",
       "      <td>1.223200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1100</td>\n",
       "      <td>1.171800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1150</td>\n",
       "      <td>1.163700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1200</td>\n",
       "      <td>1.231700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1250</td>\n",
       "      <td>1.176000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1300</td>\n",
       "      <td>1.114600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1350</td>\n",
       "      <td>1.133600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1400</td>\n",
       "      <td>1.150700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1450</td>\n",
       "      <td>1.163300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1500</td>\n",
       "      <td>1.186900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1550</td>\n",
       "      <td>1.191100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1600</td>\n",
       "      <td>1.155800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1650</td>\n",
       "      <td>1.174900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1700</td>\n",
       "      <td>1.168100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1750</td>\n",
       "      <td>1.215200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1800</td>\n",
       "      <td>1.180900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1850</td>\n",
       "      <td>1.154000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1900</td>\n",
       "      <td>1.149400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1950</td>\n",
       "      <td>1.081500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2000</td>\n",
       "      <td>1.186200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2050</td>\n",
       "      <td>1.144200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2100</td>\n",
       "      <td>1.171000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2150</td>\n",
       "      <td>1.117000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2200</td>\n",
       "      <td>1.168900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2250</td>\n",
       "      <td>1.139300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2300</td>\n",
       "      <td>1.160900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2350</td>\n",
       "      <td>1.178000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2400</td>\n",
       "      <td>1.212500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2450</td>\n",
       "      <td>1.132800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2500</td>\n",
       "      <td>1.086200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2550</td>\n",
       "      <td>1.164000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2600</td>\n",
       "      <td>1.157900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2650</td>\n",
       "      <td>1.106800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2700</td>\n",
       "      <td>1.147800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2750</td>\n",
       "      <td>1.189100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2800</td>\n",
       "      <td>1.155200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2850</td>\n",
       "      <td>1.132300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2900</td>\n",
       "      <td>1.191200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2950</td>\n",
       "      <td>1.133500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3000</td>\n",
       "      <td>1.159400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3050</td>\n",
       "      <td>1.170700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3100</td>\n",
       "      <td>1.093700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3150</td>\n",
       "      <td>1.133500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3200</td>\n",
       "      <td>1.158300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3250</td>\n",
       "      <td>1.132400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3300</td>\n",
       "      <td>1.131500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3350</td>\n",
       "      <td>1.164100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3400</td>\n",
       "      <td>1.150900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3450</td>\n",
       "      <td>1.120600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3500</td>\n",
       "      <td>1.141400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3550</td>\n",
       "      <td>1.102400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3600</td>\n",
       "      <td>1.141100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3650</td>\n",
       "      <td>1.121600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3700</td>\n",
       "      <td>1.095600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3750</td>\n",
       "      <td>1.140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3800</td>\n",
       "      <td>1.115500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3850</td>\n",
       "      <td>1.132600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3900</td>\n",
       "      <td>1.121100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3950</td>\n",
       "      <td>1.149100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4000</td>\n",
       "      <td>1.159200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4050</td>\n",
       "      <td>1.200500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4100</td>\n",
       "      <td>1.128300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4150</td>\n",
       "      <td>1.194600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4200</td>\n",
       "      <td>1.135100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4250</td>\n",
       "      <td>1.147000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4300</td>\n",
       "      <td>1.142300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4350</td>\n",
       "      <td>1.165900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4400</td>\n",
       "      <td>1.189800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4450</td>\n",
       "      <td>1.130200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4500</td>\n",
       "      <td>1.076300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4550</td>\n",
       "      <td>1.152700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4600</td>\n",
       "      <td>1.143400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4650</td>\n",
       "      <td>1.194900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4700</td>\n",
       "      <td>1.142500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4750</td>\n",
       "      <td>1.123100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4800</td>\n",
       "      <td>1.160400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4850</td>\n",
       "      <td>1.183300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4900</td>\n",
       "      <td>1.140200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4950</td>\n",
       "      <td>1.084200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5000</td>\n",
       "      <td>1.162500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5050</td>\n",
       "      <td>1.121700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5100</td>\n",
       "      <td>1.135900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5150</td>\n",
       "      <td>1.167100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5200</td>\n",
       "      <td>1.122500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5250</td>\n",
       "      <td>1.120300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5300</td>\n",
       "      <td>1.140900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5350</td>\n",
       "      <td>1.128400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5400</td>\n",
       "      <td>1.125400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5450</td>\n",
       "      <td>1.164500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5500</td>\n",
       "      <td>1.176200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5550</td>\n",
       "      <td>1.122300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5600</td>\n",
       "      <td>1.114100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5650</td>\n",
       "      <td>1.088500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5700</td>\n",
       "      <td>1.099800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5750</td>\n",
       "      <td>1.112000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5800</td>\n",
       "      <td>1.109200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5850</td>\n",
       "      <td>1.090200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5900</td>\n",
       "      <td>1.063200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5950</td>\n",
       "      <td>1.101200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6000</td>\n",
       "      <td>1.125400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6050</td>\n",
       "      <td>1.076400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6100</td>\n",
       "      <td>1.098500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6150</td>\n",
       "      <td>1.185200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6200</td>\n",
       "      <td>1.082100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6250</td>\n",
       "      <td>1.148700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6300</td>\n",
       "      <td>1.121900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6350</td>\n",
       "      <td>1.182700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6400</td>\n",
       "      <td>1.094100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6450</td>\n",
       "      <td>1.150700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6500</td>\n",
       "      <td>1.095300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6550</td>\n",
       "      <td>1.101100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6600</td>\n",
       "      <td>1.040200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6650</td>\n",
       "      <td>1.147900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6700</td>\n",
       "      <td>1.136200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6750</td>\n",
       "      <td>1.116900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6800</td>\n",
       "      <td>1.110700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6850</td>\n",
       "      <td>1.083700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6900</td>\n",
       "      <td>1.134800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6950</td>\n",
       "      <td>1.128400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7000</td>\n",
       "      <td>1.133400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7050</td>\n",
       "      <td>1.123100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7100</td>\n",
       "      <td>1.101800</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7150</td>\n",
       "      <td>1.095000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7200</td>\n",
       "      <td>1.106300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7250</td>\n",
       "      <td>1.104400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7300</td>\n",
       "      <td>1.128700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7350</td>\n",
       "      <td>1.117300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7400</td>\n",
       "      <td>1.089900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7450</td>\n",
       "      <td>1.106400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7500</td>\n",
       "      <td>1.105000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7550</td>\n",
       "      <td>1.151100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7600</td>\n",
       "      <td>1.175400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7650</td>\n",
       "      <td>1.080900</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7700</td>\n",
       "      <td>1.095400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7750</td>\n",
       "      <td>1.105500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7800</td>\n",
       "      <td>1.097500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7850</td>\n",
       "      <td>1.097400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7900</td>\n",
       "      <td>1.063100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7950</td>\n",
       "      <td>1.114200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8000</td>\n",
       "      <td>1.127700</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8050</td>\n",
       "      <td>1.142600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8100</td>\n",
       "      <td>1.094000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8150</td>\n",
       "      <td>1.154600</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8200</td>\n",
       "      <td>1.157900</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><p>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Trainer with LoRA configuration\n",
    "fine_tuning = SFTTrainer(\n",
    "    model=base_model,\n",
    "    train_dataset=training_data,\n",
    "    peft_config=peft_parameters,\n",
    "    dataset_text_field=\"text\",\n",
    "    tokenizer=llama_tokenizer,\n",
    "    args=train_params\n",
    ")\n",
    "\n",
    "# Training\n",
    "fine_tuning.train()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a7fbbe50-518f-45b2-b8e8-41fc7074181d",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# Save Model\n",
    "fine_tuning.model.save_pretrained(new_model_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cc9dc7d3-16e6-4787-b014-bb5427259860",
   "metadata": {},
   "source": [
    "# Step 4: Test the fine-tuned model with LoRA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4d970036-8fce-4b01-b0e8-88a06f27fbfd",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ignore the delete\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Loading checkpoint shards: 100%|██████████| 7/7 [04:37<00:00, 39.60s/it]\n"
     ]
    }
   ],
   "source": [
    "from peft import LoraConfig, PeftModel\n",
    "\n",
    "# Reload model in FP16 and merge it with LoRA weights\n",
    "try:\n",
    "    del base_model\n",
    "except:\n",
    "    print('Ignore the delete')\n",
    "base_model_name = \"Meta-Llama-3-8B-Instruct\"\n",
    "base_model = AutoModelForCausalLM.from_pretrained(\n",
    "    base_model_name,\n",
    "    low_cpu_mem_usage=True,\n",
    "    return_dict=True,\n",
    "   # torch_dtype=torch.float16,\n",
    "    device_map=\"auto\"\n",
    ")\n",
    "\n",
    "new_model_name = 'results_modified_v2/checkpoint-12000'\n",
    "model = PeftModel.from_pretrained(base_model, new_model_name)\n",
    "model = model.merge_and_unload()\n",
    "# Reload tokenizer to save it\n",
    "tokenizer = AutoTokenizer.from_pretrained(base_model_name, trust_remote_code=True)\n",
    "# tokenizer.pad_token = tokenizer.eos_token\n",
    "tokenizer.padding_side = \"right\"\n",
    "terminators = [\n",
    "    tokenizer.eos_token_id,\n",
    "    tokenizer.convert_tokens_to_ids(\"<|eot_id|>\")\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6a30b19f-2893-4e90-b23a-9278039a42c9",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Truncation was not explicitly activated but `max_length` is provided a specific value, please use `truncation=True` to explicitly truncate examples to max length. Defaulting to 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the tokenizer you can select this strategy more precisely by providing a specific strategy to `truncation`.\n",
      "Setting `pad_token_id` to `eos_token_id`:128009 for open-end generation.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<s>[INST] What is best restaurent in Indiana state US? [/INST] <s>What is best restaurant in Indiana state US?</s>\n",
      "\n",
      "The best restaurant in Indiana state US is subjective and depends on personal preferences. However, according to online reviews and ratings, some of the top-rated restaurants in Indiana include:\n",
      "\n",
      "* St. Elmo Steak House in Indianapolis: Known for its steaks and seafood, this restaurant has been a staple in Indiana for over 100 years.\n",
      "* The Eagle in Indianapolis: This farm-to-table restaurant offers a seasonal menu featuring locally sourced ingredients.\n",
      "* Bluebeard in Indianapolis: This upscale restaurant\n"
     ]
    }
   ],
   "source": [
    "import gc\n",
    "import torch\n",
    "\n",
    "# Call gc.collect()\n",
    "gc.collect()\n",
    "\n",
    "# Generate text using fine-tuned model\n",
    "query = \"What is best restaurent in Indiana state US?\"\n",
    "text_gen = pipeline(task=\"text-generation\", model=model, tokenizer=tokenizer, max_length=128,\n",
    "    eos_token_id=terminators,\n",
    "    do_sample=True,\n",
    "    temperature=0.6,\n",
    "    top_p=0.9,)\n",
    "output = text_gen(f\"<s>[INST] {query} [/INST]\")\n",
    "print(output[0]['generated_text'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "cade990a-19f9-496b-b31d-37a5a2b42e7a",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting `pad_token_id` to `eos_token_id`:128009 for open-end generation.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Question: Does Majestic Security offer transportation escort services?\n",
      "Context: {\"name\": \"Majestic Security\", \"address\": \"Majestic Security, 3128 Lexington Park Dr, Elkhart, IN 46514\", \"gmap_id\": \"0x8816c4b2fb8fb6a1:0x80451636e10ca83f\", \"description\": null, \"latitude\": 41.6899261, \"longitude\": -86.02416989999999, \"category\": [\"Security guard service\", \"Business to business service\", \"Public safety office\", \"Security service\", \"Training centre\", \"Training school\", \"Transportation escort service\"], \"avg_rating\": 4.3, \"num_of_reviews\": 48, \"price\": null, \"hours\": [[\"Thursday\", \"9AM–5PM\"], [\"Friday\", \"9AM–5PM\"], [\"Saturday\", \"Closed\"], [\"Sunday\", \"Closed\"], [\"Monday\", \"9AM–5PM\"], [\"Tuesday\", \"9AM–5PM\"], [\"Wednesday\", \"9AM–5PM\"]], \"MISC\": null, \"state\": \"Open ⋅ Closes 5PM\", \"relative_results\": [\"0x8816e8092cc37eff:0xa138075153591bc7\", \"0x8816ce61cc404e23:0x71a5e9e0898036a4\", \"0x8816e9eb8afbc539:0x7d7ee677df3fafa3\", \"0x8816cd46eed45c35:0x7d80db2d3b489fc3\", \"0x8816ebe5c65cf3ad:0xe8dede77091f4ecf\"], \"url\": \"https://www.google.com/maps/place//data=!4m2!3m1!1s0x8816c4b2fb8fb6a1:0x80451636e10ca83f?authuser=-1&hl=en&gl=us\"}\n",
      "\n",
      "<ANSWER>: Yes, Majestic Security offers transportation escort services. According to the business information, \"Transportation escort service\" is listed under the category of services provided by Majestic Security. ##begin_quote##Transportation escort service##end_quote##. This indicates that they do offer this type of service. <ANSWER>: Yes. ($\n"
     ]
    }
   ],
   "source": [
    "\n",
    "\n",
    "# Define the text to be processed\n",
    "data = {\n",
    "    'text': 'Question: Does Majestic Security offer transportation escort services?\\nContext: {\"name\": \"Majestic Security\", \"address\": \"Majestic Security, 3128 Lexington Park Dr, Elkhart, IN 46514\", \"gmap_id\": \"0x8816c4b2fb8fb6a1:0x80451636e10ca83f\", \"description\": null, \"latitude\": 41.6899261, \"longitude\": -86.02416989999999, \"category\": [\"Security guard service\", \"Business to business service\", \"Public safety office\", \"Security service\", \"Training centre\", \"Training school\", \"Transportation escort service\"], \"avg_rating\": 4.3, \"num_of_reviews\": 48, \"price\": null, \"hours\": [[\"Thursday\", \"9AM\\u20135PM\"], [\"Friday\", \"9AM\\u20135PM\"], [\"Saturday\", \"Closed\"], [\"Sunday\", \"Closed\"], [\"Monday\", \"9AM\\u20135PM\"], [\"Tuesday\", \"9AM\\u20135PM\"], [\"Wednesday\", \"9AM\\u20135PM\"]], \"MISC\": null, \"state\": \"Open \\u22c5 Closes 5PM\", \"relative_results\": [\"0x8816e8092cc37eff:0xa138075153591bc7\", \"0x8816ce61cc404e23:0x71a5e9e0898036a4\", \"0x8816e9eb8afbc539:0x7d7ee677df3fafa3\", \"0x8816cd46eed45c35:0x7d80db2d3b489fc3\", \"0x8816ebe5c65cf3ad:0xe8dede77091f4ecf\"], \"url\": \"https://www.google.com/maps/place//data=!4m2!3m1!1s0x8816c4b2fb8fb6a1:0x80451636e10ca83f?authuser=-1&hl=en&gl=us\"}\\n\\n<ANSWER>:',\n",
    "    'COTAnswer': 'According to the provided information, Majestic Security has an average rating of 4.3 out of 5 stars based on 48 customer reviews. While there are no specific quotes from previous customers mentioning the quality of security guards, we can infer that most customers have had a positive experience with the company.',\n",
    "    'Answer':'The majority of previous customers have been satisfied with the quality of security guards provided by Majestic Security.'\n",
    "}\n",
    "\n",
    "# Generate text using the fine-tuned model\n",
    "query = data['text']\n",
    "text_gen = pipeline(task=\"text-generation\", model=model, tokenizer=tokenizer, max_length=512, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9)\n",
    "output = text_gen(f\"{query}\")\n",
    "\n",
    "print(output[0]['generated_text'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "319b263c",
   "metadata": {},
   "source": [
    "Note: Form this I'm using my local/Colab to convert this to Q4_k_m using unloth as rocm doesn't support this"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b91c99e1",
   "metadata": {},
   "source": [
    "## Model Conversion to Q4_k_m using Unsloth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2eb6b466-425a-4ab9-8667-fee456e86f35",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/saidinesh/Desktop/Projects/gmap-recomm/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n",
      "Unsloth unsuccessfully patched LoraLayer.update_layer. Please file a bug report.\n",
      "Luckily, your training run will still work in the meantime!\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
      "==((====))==  Unsloth: Fast Llama patching release 2024.7\n",
      "   \\\\   /|    GPU: NVIDIA GeForce RTX 3070 Laptop GPU. Max memory: 7.78 GB. Platform = Linux.\n",
      "O^O/ \\_/ \\    Pytorch: 2.3.0+cu121. CUDA = 8.6. CUDA Toolkit = 12.1.\n",
      "\\        /    Bfloat16 = TRUE. FA [Xformers = 0.0.26.post1. FA2 = False]\n",
      " \"-____-\"     Free Apache license: http://github.com/unslothai/unsloth\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "unsloth/llama-3-8b-instruct-bnb-4bit does not have a padding token! Will use pad_token = <|reserved_special_token_250|>.\n",
      "Unsloth 2024.7 patched 32 layers with 0 QKV layers, 0 O layers and 0 MLP layers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Unsloth: Merging 4bit and LoRA weights to 16bit...\n",
      "Unsloth: Will use up to 13.4 out of 30.75 RAM for saving.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "  0%|          | 0/32 [00:00<?, ?it/s]We will save to Disk and not RAM now.\n",
      "100%|██████████| 32/32 [02:34<00:00,  4.81s/it]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Unsloth: Saving tokenizer... Done.\n",
      "Unsloth: Saving model... This might take 5 minutes for Llama-7b...\n",
      "Done.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Unsloth: Converting llama model. Can use fast conversion = False.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "==((====))==  Unsloth: Conversion from QLoRA to GGUF information\n",
      "   \\\\   /|    [0] Installing llama.cpp will take 3 minutes.\n",
      "O^O/ \\_/ \\    [1] Converting HF to GGUF 16bits will take 3 minutes.\n",
      "\\        /    [2] Converting GGUF 16bits to ['q4_k_m'] will take 10 minutes each.\n",
      " \"-____-\"     In total, you will have to wait at least 16 minutes.\n",
      "\n",
      "Unsloth: [0] Installing llama.cpp. This will take 3 minutes...\n",
      "Unsloth: [1] Converting model at gguf_model into bf16 GGUF format.\n",
      "The output location will be ./gguf_model/unsloth.BF16.gguf\n",
      "This will take 3 minutes...\n",
      "INFO:hf-to-gguf:Loading model: gguf_model\n",
      "INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only\n",
      "INFO:hf-to-gguf:Exporting model...\n",
      "INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'\n",
      "INFO:hf-to-gguf:gguf: loading model part 'model-00001-of-00004.safetensors'\n",
      "INFO:hf-to-gguf:token_embd.weight,           torch.bfloat16 --> BF16, shape = {4096, 128256}\n",
      "INFO:hf-to-gguf:blk.0.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.0.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.0.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.0.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.0.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.0.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.0.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.0.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.0.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.1.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.1.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.1.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.1.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.1.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.1.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.1.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.1.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.1.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.2.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.2.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.2.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.2.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.2.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.2.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.2.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.2.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.2.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.3.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.3.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.3.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.3.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.3.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.3.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.3.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.3.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.3.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.4.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.4.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.4.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.4.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.4.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.4.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.4.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.4.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.4.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.5.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.5.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.5.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.5.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.5.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.5.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.5.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.5.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.5.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.6.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.6.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.6.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.6.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.6.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.6.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.6.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.6.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.6.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.7.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.7.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.7.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.7.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.7.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.7.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.7.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.7.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.7.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.8.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.8.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.8.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.8.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.8.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.8.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.8.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.8.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.8.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:gguf: loading model part 'model-00002-of-00004.safetensors'\n",
      "INFO:hf-to-gguf:blk.10.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.10.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.10.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.10.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.10.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.10.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.10.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.10.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.10.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.11.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.11.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.11.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.11.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.11.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.11.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.11.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.11.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.11.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.12.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.12.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.12.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.12.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.12.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.12.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.12.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.12.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.12.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.13.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.13.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.13.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.13.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.13.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.13.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.13.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.13.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.13.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.14.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.14.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.14.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.14.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.14.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.14.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.14.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.14.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.14.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.15.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.15.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.15.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.15.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.15.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.15.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.15.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.15.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.15.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.16.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.16.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.16.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.16.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.16.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.16.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.16.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.16.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.16.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.17.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.17.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.17.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.17.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.17.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.17.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.17.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.17.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.17.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.18.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.18.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.18.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.18.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.18.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.18.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.18.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.18.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.18.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.19.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.19.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.19.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.19.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.19.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.19.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.19.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.19.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.19.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.20.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.20.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.20.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.20.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.20.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.9.attn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.9.ffn_down.weight,       torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.9.ffn_gate.weight,       torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.9.ffn_up.weight,         torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.9.ffn_norm.weight,       torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.9.attn_k.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.9.attn_output.weight,    torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.9.attn_q.weight,         torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.9.attn_v.weight,         torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:gguf: loading model part 'model-00003-of-00004.safetensors'\n",
      "INFO:hf-to-gguf:blk.20.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.20.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.20.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.20.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.21.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.21.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.21.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.21.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.21.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.21.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.21.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.21.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.21.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.22.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.22.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.22.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.22.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.22.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.22.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.22.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.22.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.22.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.23.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.23.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.23.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.23.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.23.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.23.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.23.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.23.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.23.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.24.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.24.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.24.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.24.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.24.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.24.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.24.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.24.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.24.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.25.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.25.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.25.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.25.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.25.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.25.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.25.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.25.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.25.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.26.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.26.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.26.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.26.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.26.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.26.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.26.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.26.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.26.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.27.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.27.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.27.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.27.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.27.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.27.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.27.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.27.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.27.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.28.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.28.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.28.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.28.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.28.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.28.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.28.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.28.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.28.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.29.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.29.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.29.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.29.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.29.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.29.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.29.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.29.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.29.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.30.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.30.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.30.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.30.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.30.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.30.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.30.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.30.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.30.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.31.ffn_gate.weight,      torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.31.ffn_up.weight,        torch.bfloat16 --> BF16, shape = {4096, 14336}\n",
      "INFO:hf-to-gguf:blk.31.attn_k.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:blk.31.attn_output.weight,   torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.31.attn_q.weight,        torch.bfloat16 --> BF16, shape = {4096, 4096}\n",
      "INFO:hf-to-gguf:blk.31.attn_v.weight,        torch.bfloat16 --> BF16, shape = {4096, 1024}\n",
      "INFO:hf-to-gguf:gguf: loading model part 'model-00004-of-00004.safetensors'\n",
      "INFO:hf-to-gguf:output.weight,               torch.bfloat16 --> BF16, shape = {4096, 128256}\n",
      "INFO:hf-to-gguf:blk.31.attn_norm.weight,     torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:blk.31.ffn_down.weight,      torch.bfloat16 --> BF16, shape = {14336, 4096}\n",
      "INFO:hf-to-gguf:blk.31.ffn_norm.weight,      torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:output_norm.weight,          torch.bfloat16 --> F32, shape = {4096}\n",
      "INFO:hf-to-gguf:Set meta model\n",
      "INFO:hf-to-gguf:Set model parameters\n",
      "INFO:hf-to-gguf:gguf: context length = 8192\n",
      "INFO:hf-to-gguf:gguf: embedding length = 4096\n",
      "INFO:hf-to-gguf:gguf: feed forward length = 14336\n",
      "INFO:hf-to-gguf:gguf: head count = 32\n",
      "INFO:hf-to-gguf:gguf: key-value head count = 8\n",
      "INFO:hf-to-gguf:gguf: rope theta = 500000.0\n",
      "INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05\n",
      "INFO:hf-to-gguf:gguf: file type = 32\n",
      "INFO:hf-to-gguf:Set model tokenizer\n",
      "INFO:gguf.vocab:Adding 280147 merge(s).\n",
      "INFO:gguf.vocab:Setting special token type bos to 128000\n",
      "INFO:gguf.vocab:Setting special token type eos to 128009\n",
      "INFO:gguf.vocab:Setting special token type pad to 128255\n",
      "INFO:gguf.vocab:Setting chat_template to {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n",
      "\n",
      "'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n",
      "\n",
      "' }}{% endif %}\n",
      "INFO:hf-to-gguf:Set model quantization version\n",
      "INFO:gguf.gguf_writer:Writing the following files:\n",
      "INFO:gguf.gguf_writer:gguf_model/unsloth.BF16.gguf: n_tensors = 291, total_size = 16.1G\n",
      "Writing: 100%|██████████| 16.1G/16.1G [03:48<00:00, 70.1Mbyte/s]\n",
      "INFO:hf-to-gguf:Model successfully exported to gguf_model/unsloth.BF16.gguf\n",
      "Unsloth: Conversion completed! Output location: ./gguf_model/unsloth.BF16.gguf\n",
      "Unsloth: [2] Converting GGUF 16bit into q4_k_m. This will take 20 minutes...\n",
      "main: build = 3455 (68504f09)\n",
      "main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu\n",
      "main: quantizing './gguf_model/unsloth.BF16.gguf' to './gguf_model/unsloth.Q4_K_M.gguf' as Q4_K_M using 32 threads\n",
      "llama_model_loader: loaded meta data with 28 key-value pairs and 291 tensors from ./gguf_model/unsloth.BF16.gguf (version GGUF V3 (latest))\n",
      "llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.\n",
      "llama_model_loader: - kv   0:                       general.architecture str              = llama\n",
      "llama_model_loader: - kv   1:                               general.type str              = model\n",
      "llama_model_loader: - kv   2:                               general.name str              = Llama 3 8b Instruct Bnb 4bit\n",
      "llama_model_loader: - kv   3:                       general.organization str              = Unsloth\n",
      "llama_model_loader: - kv   4:                           general.finetune str              = instruct-bnb-4bit\n",
      "llama_model_loader: - kv   5:                           general.basename str              = llama-3\n",
      "llama_model_loader: - kv   6:                         general.size_label str              = 8B\n",
      "llama_model_loader: - kv   7:                          llama.block_count u32              = 32\n",
      "llama_model_loader: - kv   8:                       llama.context_length u32              = 8192\n",
      "llama_model_loader: - kv   9:                     llama.embedding_length u32              = 4096\n",
      "llama_model_loader: - kv  10:                  llama.feed_forward_length u32              = 14336\n",
      "llama_model_loader: - kv  11:                 llama.attention.head_count u32              = 32\n",
      "llama_model_loader: - kv  12:              llama.attention.head_count_kv u32              = 8\n",
      "llama_model_loader: - kv  13:                       llama.rope.freq_base f32              = 500000.000000\n",
      "llama_model_loader: - kv  14:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010\n",
      "llama_model_loader: - kv  15:                          general.file_type u32              = 32\n",
      "llama_model_loader: - kv  16:                           llama.vocab_size u32              = 128256\n",
      "llama_model_loader: - kv  17:                 llama.rope.dimension_count u32              = 128\n",
      "llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2\n",
      "llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = llama-bpe\n",
      "llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,128256]  = [\"!\", \"\\\"\", \"#\", \"$\", \"%\", \"&\", \"'\", ...\n",
      "llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...\n",
      "llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,280147]  = [\"Ġ Ġ\", \"Ġ ĠĠĠ\", \"ĠĠ ĠĠ\", \"...\n",
      "llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 128000\n",
      "llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 128009\n",
      "llama_model_loader: - kv  25:            tokenizer.ggml.padding_token_id u32              = 128255\n",
      "llama_model_loader: - kv  26:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...\n",
      "llama_model_loader: - kv  27:               general.quantization_version u32              = 2\n",
      "llama_model_loader: - type  f32:   65 tensors\n",
      "llama_model_loader: - type bf16:  226 tensors\n",
      "[   1/ 291]                    token_embd.weight - [ 4096, 128256,     1,     1], type =   bf16, converting to q4_K .. size =  1002.00 MiB ->   281.81 MiB\n",
      "[   2/ 291]               blk.0.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[   3/ 291]                blk.0.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[   4/ 291]                blk.0.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[   5/ 291]                  blk.0.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[   6/ 291]                blk.0.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[   7/ 291]                  blk.0.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[   8/ 291]             blk.0.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[   9/ 291]                  blk.0.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  10/ 291]                  blk.0.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[  11/ 291]               blk.1.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  12/ 291]                blk.1.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[  13/ 291]                blk.1.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  14/ 291]                  blk.1.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  15/ 291]                blk.1.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  16/ 291]                  blk.1.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  17/ 291]             blk.1.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  18/ 291]                  blk.1.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  19/ 291]                  blk.1.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[  20/ 291]               blk.2.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  21/ 291]                blk.2.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[  22/ 291]                blk.2.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  23/ 291]                  blk.2.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  24/ 291]                blk.2.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  25/ 291]                  blk.2.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  26/ 291]             blk.2.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  27/ 291]                  blk.2.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  28/ 291]                  blk.2.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[  29/ 291]               blk.3.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  30/ 291]                blk.3.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[  31/ 291]                blk.3.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  32/ 291]                  blk.3.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  33/ 291]                blk.3.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  34/ 291]                  blk.3.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  35/ 291]             blk.3.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  36/ 291]                  blk.3.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  37/ 291]                  blk.3.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[  38/ 291]               blk.4.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  39/ 291]                blk.4.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  40/ 291]                blk.4.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  41/ 291]                  blk.4.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  42/ 291]                blk.4.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  43/ 291]                  blk.4.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  44/ 291]             blk.4.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  45/ 291]                  blk.4.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  46/ 291]                  blk.4.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  47/ 291]               blk.5.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  48/ 291]                blk.5.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  49/ 291]                blk.5.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  50/ 291]                  blk.5.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  51/ 291]                blk.5.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  52/ 291]                  blk.5.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  53/ 291]             blk.5.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  54/ 291]                  blk.5.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  55/ 291]                  blk.5.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  56/ 291]               blk.6.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  57/ 291]                blk.6.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[  58/ 291]                blk.6.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  59/ 291]                  blk.6.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  60/ 291]                blk.6.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  61/ 291]                  blk.6.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  62/ 291]             blk.6.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  63/ 291]                  blk.6.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  64/ 291]                  blk.6.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[  65/ 291]               blk.7.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  66/ 291]                blk.7.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  67/ 291]                blk.7.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  68/ 291]                  blk.7.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  69/ 291]                blk.7.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  70/ 291]                  blk.7.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  71/ 291]             blk.7.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  72/ 291]                  blk.7.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  73/ 291]                  blk.7.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  74/ 291]               blk.8.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  75/ 291]                blk.8.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  76/ 291]                blk.8.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  77/ 291]                  blk.8.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  78/ 291]                blk.8.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  79/ 291]                  blk.8.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  80/ 291]             blk.8.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  81/ 291]                  blk.8.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  82/ 291]                  blk.8.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  83/ 291]              blk.10.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  84/ 291]               blk.10.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[  85/ 291]               blk.10.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  86/ 291]                 blk.10.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  87/ 291]               blk.10.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  88/ 291]                 blk.10.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  89/ 291]            blk.10.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  90/ 291]                 blk.10.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  91/ 291]                 blk.10.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[  92/ 291]              blk.11.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  93/ 291]               blk.11.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  94/ 291]               blk.11.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  95/ 291]                 blk.11.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[  96/ 291]               blk.11.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[  97/ 291]                 blk.11.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[  98/ 291]            blk.11.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[  99/ 291]                 blk.11.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 100/ 291]                 blk.11.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 101/ 291]              blk.12.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 102/ 291]               blk.12.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 103/ 291]               blk.12.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 104/ 291]                 blk.12.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 105/ 291]               blk.12.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 106/ 291]                 blk.12.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 107/ 291]            blk.12.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 108/ 291]                 blk.12.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 109/ 291]                 blk.12.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 110/ 291]              blk.13.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 111/ 291]               blk.13.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 112/ 291]               blk.13.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 113/ 291]                 blk.13.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 114/ 291]               blk.13.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 115/ 291]                 blk.13.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 116/ 291]            blk.13.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 117/ 291]                 blk.13.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 118/ 291]                 blk.13.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 119/ 291]              blk.14.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 120/ 291]               blk.14.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 121/ 291]               blk.14.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 122/ 291]                 blk.14.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 123/ 291]               blk.14.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 124/ 291]                 blk.14.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 125/ 291]            blk.14.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 126/ 291]                 blk.14.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 127/ 291]                 blk.14.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 128/ 291]              blk.15.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 129/ 291]               blk.15.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 130/ 291]               blk.15.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 131/ 291]                 blk.15.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 132/ 291]               blk.15.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 133/ 291]                 blk.15.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 134/ 291]            blk.15.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 135/ 291]                 blk.15.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 136/ 291]                 blk.15.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 137/ 291]              blk.16.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 138/ 291]               blk.16.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 139/ 291]               blk.16.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 140/ 291]                 blk.16.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 141/ 291]               blk.16.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 142/ 291]                 blk.16.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 143/ 291]            blk.16.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 144/ 291]                 blk.16.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 145/ 291]                 blk.16.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 146/ 291]              blk.17.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 147/ 291]               blk.17.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 148/ 291]               blk.17.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 149/ 291]                 blk.17.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 150/ 291]               blk.17.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 151/ 291]                 blk.17.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 152/ 291]            blk.17.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 153/ 291]                 blk.17.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 154/ 291]                 blk.17.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 155/ 291]              blk.18.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 156/ 291]               blk.18.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 157/ 291]               blk.18.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 158/ 291]                 blk.18.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 159/ 291]               blk.18.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 160/ 291]                 blk.18.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 161/ 291]            blk.18.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 162/ 291]                 blk.18.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 163/ 291]                 blk.18.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 164/ 291]              blk.19.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 165/ 291]               blk.19.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 166/ 291]               blk.19.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 167/ 291]                 blk.19.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 168/ 291]               blk.19.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 169/ 291]                 blk.19.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 170/ 291]            blk.19.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 171/ 291]                 blk.19.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 172/ 291]                 blk.19.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 173/ 291]               blk.20.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 174/ 291]                 blk.20.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 175/ 291]            blk.20.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 176/ 291]                 blk.20.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 177/ 291]                 blk.20.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 178/ 291]               blk.9.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 179/ 291]                blk.9.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 180/ 291]                blk.9.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 181/ 291]                  blk.9.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 182/ 291]                blk.9.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 183/ 291]                  blk.9.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 184/ 291]             blk.9.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 185/ 291]                  blk.9.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 186/ 291]                  blk.9.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 187/ 291]              blk.20.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 188/ 291]               blk.20.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 189/ 291]                 blk.20.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 190/ 291]               blk.20.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 191/ 291]              blk.21.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 192/ 291]               blk.21.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 193/ 291]               blk.21.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 194/ 291]                 blk.21.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 195/ 291]               blk.21.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 196/ 291]                 blk.21.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 197/ 291]            blk.21.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 198/ 291]                 blk.21.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 199/ 291]                 blk.21.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 200/ 291]              blk.22.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 201/ 291]               blk.22.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 202/ 291]               blk.22.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 203/ 291]                 blk.22.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 204/ 291]               blk.22.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 205/ 291]                 blk.22.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 206/ 291]            blk.22.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 207/ 291]                 blk.22.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 208/ 291]                 blk.22.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 209/ 291]              blk.23.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 210/ 291]               blk.23.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 211/ 291]               blk.23.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 212/ 291]                 blk.23.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 213/ 291]               blk.23.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 214/ 291]                 blk.23.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 215/ 291]            blk.23.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 216/ 291]                 blk.23.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 217/ 291]                 blk.23.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 218/ 291]              blk.24.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 219/ 291]               blk.24.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 220/ 291]               blk.24.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 221/ 291]                 blk.24.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 222/ 291]               blk.24.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 223/ 291]                 blk.24.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 224/ 291]            blk.24.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 225/ 291]                 blk.24.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 226/ 291]                 blk.24.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 227/ 291]              blk.25.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 228/ 291]               blk.25.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 229/ 291]               blk.25.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 230/ 291]                 blk.25.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 231/ 291]               blk.25.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 232/ 291]                 blk.25.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 233/ 291]            blk.25.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 234/ 291]                 blk.25.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 235/ 291]                 blk.25.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 236/ 291]              blk.26.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 237/ 291]               blk.26.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 238/ 291]               blk.26.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 239/ 291]                 blk.26.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 240/ 291]               blk.26.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 241/ 291]                 blk.26.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 242/ 291]            blk.26.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 243/ 291]                 blk.26.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 244/ 291]                 blk.26.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 245/ 291]              blk.27.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 246/ 291]               blk.27.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 247/ 291]               blk.27.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 248/ 291]                 blk.27.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 249/ 291]               blk.27.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 250/ 291]                 blk.27.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 251/ 291]            blk.27.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 252/ 291]                 blk.27.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 253/ 291]                 blk.27.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 254/ 291]              blk.28.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 255/ 291]               blk.28.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 256/ 291]               blk.28.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 257/ 291]                 blk.28.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 258/ 291]               blk.28.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 259/ 291]                 blk.28.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 260/ 291]            blk.28.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 261/ 291]                 blk.28.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 262/ 291]                 blk.28.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 263/ 291]              blk.29.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 264/ 291]               blk.29.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 265/ 291]               blk.29.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 266/ 291]                 blk.29.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 267/ 291]               blk.29.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 268/ 291]                 blk.29.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 269/ 291]            blk.29.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 270/ 291]                 blk.29.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 271/ 291]                 blk.29.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 272/ 291]              blk.30.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 273/ 291]               blk.30.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 274/ 291]               blk.30.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 275/ 291]                 blk.30.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 276/ 291]               blk.30.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 277/ 291]                 blk.30.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 278/ 291]            blk.30.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 279/ 291]                 blk.30.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 280/ 291]                 blk.30.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 281/ 291]               blk.31.ffn_gate.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 282/ 291]                 blk.31.ffn_up.weight - [ 4096, 14336,     1,     1], type =   bf16, converting to q4_K .. size =   112.00 MiB ->    31.50 MiB\n",
      "[ 283/ 291]                 blk.31.attn_k.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q4_K .. size =     8.00 MiB ->     2.25 MiB\n",
      "[ 284/ 291]            blk.31.attn_output.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 285/ 291]                 blk.31.attn_q.weight - [ 4096,  4096,     1,     1], type =   bf16, converting to q4_K .. size =    32.00 MiB ->     9.00 MiB\n",
      "[ 286/ 291]                 blk.31.attn_v.weight - [ 4096,  1024,     1,     1], type =   bf16, converting to q6_K .. size =     8.00 MiB ->     3.28 MiB\n",
      "[ 287/ 291]                        output.weight - [ 4096, 128256,     1,     1], type =   bf16, converting to q6_K .. size =  1002.00 MiB ->   410.98 MiB\n",
      "[ 288/ 291]              blk.31.attn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 289/ 291]               blk.31.ffn_down.weight - [14336,  4096,     1,     1], type =   bf16, converting to q6_K .. size =   112.00 MiB ->    45.94 MiB\n",
      "[ 290/ 291]               blk.31.ffn_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "[ 291/ 291]                   output_norm.weight - [ 4096,     1,     1,     1], type =    f32, size =    0.016 MB\n",
      "llama_model_quantize_internal: model size  = 15317.02 MB\n",
      "llama_model_quantize_internal: quant size  =  4685.30 MB\n",
      "\n",
      "main: quantize time = 182435.40 ms\n",
      "main:    total time = 182435.40 ms\n",
      "Unsloth: Conversion completed! Output location: ./gguf_model/unsloth.Q4_K_M.gguf\n"
     ]
    }
   ],
   "source": [
    "#!pip install \"unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git\"\n",
    "from unsloth import FastLanguageModel\n",
    "model, tokenizer = FastLanguageModel.from_pretrained(\"../checkpoint_12000\")\n",
    "model.save_pretrained_gguf(\"gguf_model\", tokenizer, quantization_method = \"q4_k_m\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4c43675",
   "metadata": {},
   "source": [
    "## Ollama model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3da03831",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[?25ltransferring model data ⠙ \u001b[?25h"
     ]
    },
    {
     "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"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠹ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠸ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠼ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠴ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠦ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠧ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠇ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠏ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠋ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data ⠙ \u001b[?25h\u001b[?25l\u001b[2K\u001b[1Gtransferring model data \n",
      "using existing layer sha256:5c2af956574e0da0392b287e464109750b892e8af8445fd930cbaba1bd7502f4 \n",
      "using existing layer sha256:8ab4849b038cf0abc5b1c9b8ee1443dca6b93a045c2272180d985126eb40bf6f \n",
      "creating new layer sha256:64908564276ea276619a01ffa02c38972938f56b80f02f271d2ed2d78128fff3 \n",
      "using existing layer sha256:577073ffcc6ce95b9981eacc77d1039568639e5638e83044994560d9ef82ce1b \n",
      "creating new layer sha256:13ea84eca7e0d06ca18290ac4ef51fcb96e2539c48f63e3c28ea84766fec043d \n",
      "writing manifest \n",
      "success \u001b[?25h\n"
     ]
    }
   ],
   "source": [
    "!ollama create gmap_recomm_llama3 -f ./gguf_model/Modelfile"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a7540f1",
   "metadata": {},
   "source": [
    "Check the newly created gmap_recomm_llama3 model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ae3381e2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "NAME                     \tID          \tSIZE  \tMODIFIED       \n",
      "gmap_recomm_llama3:latest\t3a8dba601c00\t4.9 GB\t32 seconds ago\t\n",
      "llama3:latest            \t365c0bd3c000\t4.7 GB\t6 weeks ago   \t\n"
     ]
    },
    {
     "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": [
    "!ollama list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "553451dc",
   "metadata": {},
   "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"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"model\":\"gmap_recomm_llama3\",\"created_at\":\"2024-07-25T05:40:22.788234638Z\",\"response\":\"What a great question!\\n\\nThe short answer: The sky appears blue because of a phenomenon called Rayleigh scattering, which occurs when sunlight interacts with tiny molecules of gases in Earth's atmosphere.\\n\\nA bit more detail:\\n\\nWhen sunlight enters our atmosphere, it encounters tiny molecules of gases like nitrogen (N2) and oxygen (O2). These molecules are so small that they can scatter the light in all directions. However, shorter wavelengths (like blue and violet light) are scattered more than longer wavelengths (like red and orange light).\\n\\nThis is because smaller molecules are better at scattering shorter wavelengths due to their smaller size and greater surface area-to-volume ratio. As a result, our eyes perceive the blue color as the dominant wavelength that's being scattered in all directions.\\n\\nThe blue color we see is also influenced by other atmospheric conditions, such as:\\n\\n1. Mie scattering: Scattering caused by larger particles like dust, pollen, or water droplets, which can scatter longer wavelengths (like red and orange light) more than shorter ones.\\n2. Atmospheric absorption: The absorption of certain wavelengths (like ultraviolet and infrared) by gases and aerosols in the atmosphere, which affects the color we see.\\n\\nThe combination of Rayleigh scattering, Mie scattering, and atmospheric absorption gives us the blue sky we enjoy!\\n\\nWould you like to know more about this topic or is there something else I can help with?\",\"done\":true,\"done_reason\":\"stop\",\"context\":[128006,882,128007,271,10445,374,279,13180,6437,30,128009,128006,78191,128007,271,3923,264,2294,3488,2268,791,2875,4320,25,578,13180,8111,6437,1606,315,264,25885,2663,13558,64069,72916,11,902,13980,994,40120,84261,449,13987,35715,315,45612,304,9420,596,16975,382,32,2766,810,7872,1473,4599,40120,29933,1057,16975,11,433,35006,13987,35715,315,45612,1093,47503,320,45,17,8,323,24463,320,46,17,570,4314,35715,527,779,2678,430,814,649,45577,279,3177,304,682,18445,13,4452,11,24210,93959,320,4908,6437,323,80836,3177,8,527,38067,810,1109,5129,93959,320,4908,2579,323,19087,3177,3677,2028,374,1606,9333,35715,527,2731,520,72916,24210,93959,4245,311,872,9333,1404,323,7191,7479,3158,4791,67868,11595,13,1666,264,1121,11,1057,6548,45493,279,6437,1933,439,279,25462,46406,430,596,1694,38067,304,682,18445,382,791,6437,1933,584,1518,374,1101,28160,555,1023,45475,4787,11,1778,439,1473,16,13,386,648,72916,25,2522,31436,9057,555,8294,19252,1093,16174,11,79784,11,477,3090,7118,90592,11,902,649,45577,5129,93959,320,4908,2579,323,19087,3177,8,810,1109,24210,6305,627,17,13,87597,44225,25,578,44225,315,3738,93959,320,4908,37232,85311,323,59141,8,555,45612,323,49825,3145,304,279,16975,11,902,22223,279,1933,584,1518,382,791,10824,315,13558,64069,72916,11,386,648,72916,11,323,45475,44225,6835,603,279,6437,13180,584,4774,2268,29089,499,1093,311,1440,810,922,420,8712,477,374,1070,2555,775,358,649,1520,449,30,128009],\"total_duration\":49871622415,\"load_duration\":1620903,\"prompt_eval_duration\":159363000,\"eval_count\":281,\"eval_duration\":49665261000}"
     ]
    }
   ],
   "source": [
    "\n",
    "!curl -XPOST localhost:11434/api/generate -d '{\"model\": \"gmap_recomm_llama3\", \"prompt\": \"Why is the sky blue?\", \"stream\": false }'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "07978020",
   "metadata": {},
   "source": [
    "ThankYou🙏"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}