13B_HyperMantis_GPTQ_4bit_128g.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "authorship_tag": "ABX9TyPDpads5HkU9s0LpDvnExiW",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Troyanovsky/Local-LLM-comparison/blob/main/13B_HyperMantis_GPTQ_4bit_128g.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## 13B-HyperMantis_GPTQ_4bit-128g WebUI\n",
        "1. Run the following cell, takes ~5 min\n",
        "2. Click the gradio link at the bottom\n",
        "3. In Chat settings - Instruction Template: Change to Alpaca\n",
        "\n",
        "[Ref](https://huggingface.co/digitous/13B-HyperMantis):\n",
        "```\n",
        "Subjective testing shows quality results with KoboldAI (similar results are likely in Text Generation Webui, please disregard KAI-centric settings for that platform); Godlike preset with these tweaks - 2048 context, 800 Output Length, 1.3 Temp, 1.13 Repetition Penalty, AltTextGen:On, AltRepPen:Off, No Prompt Gen:On\n",
        "```"
      ],
      "metadata": {
        "id": "XNkpBtLvuTOp"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "D-MiHp_bveP6",
        "outputId": "3b01f209-2450-499d-e6da-53fab1ec2d92"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content\n",
            "Selecting previously unselected package libc-ares2:amd64.\n",
            "(Reading database ... 122542 files and directories currently installed.)\n",
            "Preparing to unpack .../libc-ares2_1.15.0-1ubuntu0.2_amd64.deb ...\n",
            "Unpacking libc-ares2:amd64 (1.15.0-1ubuntu0.2) ...\n",
            "Selecting previously unselected package libaria2-0:amd64.\n",
            "Preparing to unpack .../libaria2-0_1.35.0-1build1_amd64.deb ...\n",
            "Unpacking libaria2-0:amd64 (1.35.0-1build1) ...\n",
            "Selecting previously unselected package aria2.\n",
            "Preparing to unpack .../aria2_1.35.0-1build1_amd64.deb ...\n",
            "Unpacking aria2 (1.35.0-1build1) ...\n",
            "Setting up libc-ares2:amd64 (1.15.0-1ubuntu0.2) ...\n",
            "Setting up libaria2-0:amd64 (1.35.0-1build1) ...\n",
            "Setting up aria2 (1.35.0-1build1) ...\n",
            "Processing triggers for man-db (2.9.1-1) ...\n",
            "Processing triggers for libc-bin (2.31-0ubuntu9.9) ...\n",
            "Cloning into 'text-generation-webui'...\n",
            "remote: Enumerating objects: 7938, done.\u001b[K\n",
            "remote: Counting objects: 100% (156/156), done.\u001b[K\n",
            "remote: Compressing objects: 100% (69/69), done.\u001b[K\n",
            "remote: Total 7938 (delta 90), reused 135 (delta 87), pack-reused 7782\u001b[K\n",
            "Receiving objects: 100% (7938/7938), 2.76 MiB | 28.80 MiB/s, done.\n",
            "Resolving deltas: 100% (5296/5296), done.\n",
            "Note: switching to '7dc87984a2347794beed957a1923203b70a597b9'.\n",
            "\n",
            "You are in 'detached HEAD' state. You can look around, make experimental\n",
            "changes and commit them, and you can discard any commits you make in this\n",
            "state without impacting any branches by switching back to a branch.\n",
            "\n",
            "If you want to create a new branch to retain commits you create, you may\n",
            "do so (now or later) by using -c with the switch command. Example:\n",
            "\n",
            "  git switch -c <new-branch-name>\n",
            "\n",
            "Or undo this operation with:\n",
            "\n",
            "  git switch -\n",
            "\n",
            "Turn off this advice by setting config variable advice.detachedHead to false\n",
            "\n",
            "/content/text-generation-webui\n",
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Collecting git+https://github.com/huggingface/peft@4fd374e80d670781c0d82c96ce94d1215ff23306 (from -r requirements.txt (line 17))\n",
            "  Cloning https://github.com/huggingface/peft (to revision 4fd374e80d670781c0d82c96ce94d1215ff23306) to /tmp/pip-req-build-ue2zkgck\n",
            "  Running command git clone --filter=blob:none --quiet https://github.com/huggingface/peft /tmp/pip-req-build-ue2zkgck\n",
            "  Running command git rev-parse -q --verify 'sha^4fd374e80d670781c0d82c96ce94d1215ff23306'\n",
            "  Running command git fetch -q https://github.com/huggingface/peft 4fd374e80d670781c0d82c96ce94d1215ff23306\n",
            "  Running command git checkout -q 4fd374e80d670781c0d82c96ce94d1215ff23306\n",
            "  Resolved https://github.com/huggingface/peft to commit 4fd374e80d670781c0d82c96ce94d1215ff23306\n",
            "  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "Ignoring llama-cpp-python: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Collecting accelerate==0.19.0 (from -r requirements.txt (line 1))\n",
            "  Downloading accelerate-0.19.0-py3-none-any.whl (219 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m219.1/219.1 kB\u001b[0m \u001b[31m22.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting colorama (from -r requirements.txt (line 2))\n",
            "  Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
            "Collecting datasets (from -r requirements.txt (line 3))\n",
            "  Downloading datasets-2.12.0-py3-none-any.whl (474 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m474.6/474.6 kB\u001b[0m \u001b[31m45.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting flexgen==0.1.7 (from -r requirements.txt (line 4))\n",
            "  Downloading flexgen-0.1.7-py3-none-any.whl (50 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.8/50.8 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting gradio_client==0.2.5 (from -r requirements.txt (line 5))\n",
            "  Downloading gradio_client-0.2.5-py3-none-any.whl (288 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m288.1/288.1 kB\u001b[0m \u001b[31m37.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting gradio==3.31.0 (from -r requirements.txt (line 6))\n",
            "  Downloading gradio-3.31.0-py3-none-any.whl (17.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.4/17.4 MB\u001b[0m \u001b[31m95.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: markdown in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 7)) (3.4.3)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 8)) (1.22.4)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 9)) (1.5.3)\n",
            "Collecting Pillow>=9.5.0 (from -r requirements.txt (line 10))\n",
            "  Downloading Pillow-9.5.0-cp310-cp310-manylinux_2_28_x86_64.whl (3.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m105.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 11)) (6.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 12)) (2.27.1)\n",
            "Collecting safetensors==0.3.1 (from -r requirements.txt (line 13))\n",
            "  Downloading safetensors-0.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m90.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting sentencepiece (from -r requirements.txt (line 14))\n",
            "  Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m92.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting transformers==4.29.2 (from -r requirements.txt (line 15))\n",
            "  Downloading transformers-4.29.2-py3-none-any.whl (7.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.1/7.1 MB\u001b[0m \u001b[31m124.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 16)) (4.65.0)\n",
            "Collecting bitsandbytes==0.38.1 (from -r requirements.txt (line 18))\n",
            "  Downloading bitsandbytes-0.38.1-py3-none-any.whl (104.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m104.3/104.3 MB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting llama-cpp-python==0.1.51 (from -r requirements.txt (line 19))\n",
            "  Downloading llama_cpp_python-0.1.51.tar.gz (1.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m69.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.19.0->-r requirements.txt (line 1)) (23.1)\n",
            "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate==0.19.0->-r requirements.txt (line 1)) (5.9.5)\n",
            "Requirement already satisfied: torch>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.19.0->-r requirements.txt (line 1)) (2.0.1+cu118)\n",
            "Collecting pulp (from flexgen==0.1.7->-r requirements.txt (line 4))\n",
            "  Downloading PuLP-2.7.0-py3-none-any.whl (14.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.3/14.3 MB\u001b[0m \u001b[31m112.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: attrs in /usr/local/lib/python3.10/dist-packages (from flexgen==0.1.7->-r requirements.txt (line 4)) (23.1.0)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio_client==0.2.5->-r requirements.txt (line 5)) (2023.4.0)\n",
            "Collecting httpx (from gradio_client==0.2.5->-r requirements.txt (line 5))\n",
            "  Downloading httpx-0.24.1-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.4/75.4 kB\u001b[0m \u001b[31m11.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting huggingface-hub>=0.13.0 (from gradio_client==0.2.5->-r requirements.txt (line 5))\n",
            "  Downloading huggingface_hub-0.15.1-py3-none-any.whl (236 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m236.8/236.8 kB\u001b[0m \u001b[31m23.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from gradio_client==0.2.5->-r requirements.txt (line 5)) (4.5.0)\n",
            "Collecting websockets (from gradio_client==0.2.5->-r requirements.txt (line 5))\n",
            "  Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m818.7 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting aiofiles (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading aiofiles-23.1.0-py3-none-any.whl (14 kB)\n",
            "Collecting aiohttp (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading aiohttp-3.8.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m75.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: altair>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.31.0->-r requirements.txt (line 6)) (4.2.2)\n",
            "Collecting fastapi (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading fastapi-0.96.0-py3-none-any.whl (57 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.1/57.1 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting ffmpy (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading ffmpy-0.3.0.tar.gz (4.8 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from gradio==3.31.0->-r requirements.txt (line 6)) (3.1.2)\n",
            "Requirement already satisfied: markdown-it-py[linkify]>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.31.0->-r requirements.txt (line 6)) (2.2.0)\n",
            "Requirement already satisfied: markupsafe in /usr/local/lib/python3.10/dist-packages (from gradio==3.31.0->-r requirements.txt (line 6)) (2.1.2)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from gradio==3.31.0->-r requirements.txt (line 6)) (3.7.1)\n",
            "Collecting mdit-py-plugins<=0.3.3 (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading mdit_py_plugins-0.3.3-py3-none-any.whl (50 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.5/50.5 kB\u001b[0m \u001b[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting orjson (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading orjson-3.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (136 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m137.0/137.0 kB\u001b[0m \u001b[31m19.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pydantic in /usr/local/lib/python3.10/dist-packages (from gradio==3.31.0->-r requirements.txt (line 6)) (1.10.7)\n",
            "Collecting pydub (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
            "Requirement already satisfied: pygments>=2.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.31.0->-r requirements.txt (line 6)) (2.14.0)\n",
            "Collecting python-multipart (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading python_multipart-0.0.6-py3-none-any.whl (45 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.7/45.7 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting semantic-version (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
            "Collecting uvicorn>=0.14.0 (from gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading uvicorn-0.22.0-py3-none-any.whl (58 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.29.2->-r requirements.txt (line 15)) (3.12.0)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.29.2->-r requirements.txt (line 15)) (2022.10.31)\n",
            "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers==4.29.2->-r requirements.txt (line 15))\n",
            "  Downloading tokenizers-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m122.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets->-r requirements.txt (line 3)) (9.0.0)\n",
            "Collecting dill<0.3.7,>=0.3.0 (from datasets->-r requirements.txt (line 3))\n",
            "  Downloading dill-0.3.6-py3-none-any.whl (110 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m110.5/110.5 kB\u001b[0m \u001b[31m16.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting xxhash (from datasets->-r requirements.txt (line 3))\n",
            "  Downloading xxhash-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (212 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m212.5/212.5 kB\u001b[0m \u001b[31m27.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting multiprocess (from datasets->-r requirements.txt (line 3))\n",
            "  Downloading multiprocess-0.70.14-py310-none-any.whl (134 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.3/134.3 kB\u001b[0m \u001b[31m20.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting responses<0.19 (from datasets->-r requirements.txt (line 3))\n",
            "  Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 9)) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 9)) (2022.7.1)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 12)) (1.26.15)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 12)) (2022.12.7)\n",
            "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 12)) (2.0.12)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 12)) (3.4)\n",
            "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.31.0->-r requirements.txt (line 6)) (0.4)\n",
            "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.31.0->-r requirements.txt (line 6)) (4.3.3)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.31.0->-r requirements.txt (line 6)) (0.12.0)\n",
            "Collecting multidict<7.0,>=4.5 (from aiohttp->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.5/114.5 kB\u001b[0m \u001b[31m16.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting async-timeout<5.0,>=4.0.0a3 (from aiohttp->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n",
            "Collecting yarl<2.0,>=1.0 (from aiohttp->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading yarl-1.9.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (268 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m268.8/268.8 kB\u001b[0m \u001b[31m31.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting frozenlist>=1.1.1 (from aiohttp->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading frozenlist-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (149 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m149.6/149.6 kB\u001b[0m \u001b[31m17.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting aiosignal>=1.1.2 (from aiohttp->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio==3.31.0->-r requirements.txt (line 6)) (0.1.2)\n",
            "Collecting linkify-it-py<3,>=1 (from markdown-it-py[linkify]>=2.0.0->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading linkify_it_py-2.0.2-py3-none-any.whl (19 kB)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->-r requirements.txt (line 9)) (1.16.0)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate==0.19.0->-r requirements.txt (line 1)) (1.11.1)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate==0.19.0->-r requirements.txt (line 1)) (3.1)\n",
            "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate==0.19.0->-r requirements.txt (line 1)) (2.0.0)\n",
            "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.6.0->accelerate==0.19.0->-r requirements.txt (line 1)) (3.25.2)\n",
            "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.6.0->accelerate==0.19.0->-r requirements.txt (line 1)) (16.0.5)\n",
            "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio==3.31.0->-r requirements.txt (line 6)) (8.1.3)\n",
            "Collecting h11>=0.8 (from uvicorn>=0.14.0->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting starlette<0.28.0,>=0.27.0 (from fastapi->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading starlette-0.27.0-py3-none-any.whl (66 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.0/67.0 kB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting httpcore<0.18.0,>=0.15.0 (from httpx->gradio_client==0.2.5->-r requirements.txt (line 5))\n",
            "  Downloading httpcore-0.17.2-py3-none-any.whl (72 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m72.5/72.5 kB\u001b[0m \u001b[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio_client==0.2.5->-r requirements.txt (line 5)) (1.3.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.31.0->-r requirements.txt (line 6)) (1.0.7)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.31.0->-r requirements.txt (line 6)) (0.11.0)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.31.0->-r requirements.txt (line 6)) (4.39.3)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.31.0->-r requirements.txt (line 6)) (1.4.4)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.31.0->-r requirements.txt (line 6)) (3.0.9)\n",
            "Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from httpcore<0.18.0,>=0.15.0->httpx->gradio_client==0.2.5->-r requirements.txt (line 5)) (3.6.2)\n",
            "Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio==3.31.0->-r requirements.txt (line 6)) (0.19.3)\n",
            "Collecting uc-micro-py (from linkify-it-py<3,>=1->markdown-it-py[linkify]>=2.0.0->gradio==3.31.0->-r requirements.txt (line 6))\n",
            "  Downloading uc_micro_py-1.0.2-py3-none-any.whl (6.2 kB)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.6.0->accelerate==0.19.0->-r requirements.txt (line 1)) (1.3.0)\n",
            "Building wheels for collected packages: llama-cpp-python, peft, ffmpy\n",
            "  Building wheel for llama-cpp-python (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for llama-cpp-python: filename=llama_cpp_python-0.1.51-cp310-cp310-linux_x86_64.whl size=206449 sha256=ef20d42af7c890654cb9d52617c8dfdea9fe25bd083a8d1e587453ebc1664f05\n",
            "  Stored in directory: /root/.cache/pip/wheels/df/ee/66/1fc3c013ec57fbf77814781e1805582ed481819eb912d2bf25\n",
            "  Building wheel for peft (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for peft: filename=peft-0.4.0.dev0-py3-none-any.whl size=56306 sha256=600b666d7c6ad46b862df31c9edf9f256e7c3d51f9136b2a7c0b65bb57ab6dac\n",
            "  Stored in directory: /root/.cache/pip/wheels/bd/04/7b/496ab9ebd4f1352e3b8178f637ac2d3d3fce67621b753cc75b\n",
            "  Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for ffmpy: filename=ffmpy-0.3.0-py3-none-any.whl size=4694 sha256=f9c4137264b3532e59fd393b03ffa9f58e46b88e670e3fd5099ad7e701ef648a\n",
            "  Stored in directory: /root/.cache/pip/wheels/0c/c2/0e/3b9c6845c6a4e35beb90910cc70d9ac9ab5d47402bd62af0df\n",
            "Successfully built llama-cpp-python peft ffmpy\n",
            "Installing collected packages: tokenizers, sentencepiece, safetensors, pydub, pulp, ffmpy, bitsandbytes, xxhash, websockets, uc-micro-py, semantic-version, python-multipart, Pillow, orjson, multidict, llama-cpp-python, h11, frozenlist, dill, colorama, async-timeout, aiofiles, yarl, uvicorn, starlette, responses, multiprocess, mdit-py-plugins, linkify-it-py, huggingface-hub, httpcore, aiosignal, transformers, httpx, fastapi, aiohttp, gradio_client, gradio, datasets, accelerate, peft, flexgen\n",
            "  Attempting uninstall: Pillow\n",
            "    Found existing installation: Pillow 8.4.0\n",
            "    Uninstalling Pillow-8.4.0:\n",
            "      Successfully uninstalled Pillow-8.4.0\n",
            "Successfully installed Pillow-9.5.0 accelerate-0.19.0 aiofiles-23.1.0 aiohttp-3.8.4 aiosignal-1.3.1 async-timeout-4.0.2 bitsandbytes-0.38.1 colorama-0.4.6 datasets-2.12.0 dill-0.3.6 fastapi-0.96.0 ffmpy-0.3.0 flexgen-0.1.7 frozenlist-1.3.3 gradio-3.31.0 gradio_client-0.2.5 h11-0.14.0 httpcore-0.17.2 httpx-0.24.1 huggingface-hub-0.15.1 linkify-it-py-2.0.2 llama-cpp-python-0.1.51 mdit-py-plugins-0.3.3 multidict-6.0.4 multiprocess-0.70.14 orjson-3.9.0 peft-0.4.0.dev0 pulp-2.7.0 pydub-0.25.1 python-multipart-0.0.6 responses-0.18.0 safetensors-0.3.1 semantic-version-2.10.0 sentencepiece-0.1.99 starlette-0.27.0 tokenizers-0.13.3 transformers-4.29.2 uc-micro-py-1.0.2 uvicorn-0.22.0 websockets-11.0.3 xxhash-3.2.0 yarl-1.9.2\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "PIL"
                ]
              }
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Collecting gradio==3.32.0\n",
            "  Downloading gradio-3.32.0-py3-none-any.whl (19.9 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m19.9/19.9 MB\u001b[0m \u001b[31m89.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: aiofiles in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (23.1.0)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (3.8.4)\n",
            "Requirement already satisfied: altair>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (4.2.2)\n",
            "Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.96.0)\n",
            "Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.3.0)\n",
            "Requirement already satisfied: gradio-client>=0.2.4 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.2.5)\n",
            "Requirement already satisfied: httpx in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.24.1)\n",
            "Requirement already satisfied: huggingface-hub>=0.13.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.15.1)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (3.1.2)\n",
            "Requirement already satisfied: markdown-it-py[linkify]>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (2.2.0)\n",
            "Requirement already satisfied: markupsafe in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (2.1.2)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (3.7.1)\n",
            "Requirement already satisfied: mdit-py-plugins<=0.3.3 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.3.3)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (1.22.4)\n",
            "Requirement already satisfied: orjson in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (3.9.0)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (1.5.3)\n",
            "Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (9.5.0)\n",
            "Requirement already satisfied: pydantic in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (1.10.7)\n",
            "Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.25.1)\n",
            "Requirement already satisfied: pygments>=2.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (2.14.0)\n",
            "Requirement already satisfied: python-multipart in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.0.6)\n",
            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (6.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (2.27.1)\n",
            "Requirement already satisfied: semantic-version in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (2.10.0)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (4.5.0)\n",
            "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (0.22.0)\n",
            "Requirement already satisfied: websockets>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.32.0) (11.0.3)\n",
            "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.32.0) (0.4)\n",
            "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.32.0) (4.3.3)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.32.0) (0.12.0)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client>=0.2.4->gradio==3.32.0) (2023.4.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio-client>=0.2.4->gradio==3.32.0) (23.1)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.13.0->gradio==3.32.0) (3.12.0)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.13.0->gradio==3.32.0) (4.65.0)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio==3.32.0) (0.1.2)\n",
            "Requirement already satisfied: linkify-it-py<3,>=1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio==3.32.0) (2.0.2)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->gradio==3.32.0) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->gradio==3.32.0) (2022.7.1)\n",
            "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio==3.32.0) (8.1.3)\n",
            "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio==3.32.0) (0.14.0)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.32.0) (23.1.0)\n",
            "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.32.0) (2.0.12)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.32.0) (6.0.4)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.32.0) (4.0.2)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.32.0) (1.9.2)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.32.0) (1.3.3)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.32.0) (1.3.1)\n",
            "Requirement already satisfied: starlette<0.28.0,>=0.27.0 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio==3.32.0) (0.27.0)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.32.0) (2022.12.7)\n",
            "Requirement already satisfied: httpcore<0.18.0,>=0.15.0 in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.32.0) (0.17.2)\n",
            "Requirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.32.0) (3.4)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.32.0) (1.3.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.32.0) (1.0.7)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.32.0) (0.11.0)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.32.0) (4.39.3)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.32.0) (1.4.4)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.32.0) (3.0.9)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->gradio==3.32.0) (1.26.15)\n",
            "Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from httpcore<0.18.0,>=0.15.0->httpx->gradio==3.32.0) (3.6.2)\n",
            "Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio==3.32.0) (0.19.3)\n",
            "Requirement already satisfied: uc-micro-py in /usr/local/lib/python3.10/dist-packages (from linkify-it-py<3,>=1->markdown-it-py[linkify]>=2.0.0->gradio==3.32.0) (1.0.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->gradio==3.32.0) (1.16.0)\n",
            "Installing collected packages: gradio\n",
            "  Attempting uninstall: gradio\n",
            "    Found existing installation: gradio 3.31.0\n",
            "    Uninstalling gradio-3.31.0:\n",
            "      Successfully uninstalled gradio-3.31.0\n",
            "Successfully installed gradio-3.32.0\n",
            "/content/text-generation-webui/repositories\n",
            "Cloning into 'GPTQ-for-LLaMa'...\n",
            "remote: Enumerating objects: 818, done.\u001b[K\n",
            "remote: Counting objects: 100% (419/419), done.\u001b[K\n",
            "remote: Compressing objects: 100% (25/25), done.\u001b[K\n",
            "remote: Total 818 (delta 402), reused 395 (delta 394), pack-reused 399\u001b[K\n",
            "Receiving objects: 100% (818/818), 470.02 KiB | 682.00 KiB/s, done.\n",
            "Resolving deltas: 100% (497/497), done.\n",
            "Note: switching to '53a2aeac935b7eef0e1451eb7b465fea4f318e7a'.\n",
            "\n",
            "You are in 'detached HEAD' state. You can look around, make experimental\n",
            "changes and commit them, and you can discard any commits you make in this\n",
            "state without impacting any branches by switching back to a branch.\n",
            "\n",
            "If you want to create a new branch to retain commits you create, you may\n",
            "do so (now or later) by using -c with the switch command. Example:\n",
            "\n",
            "  git switch -c <new-branch-name>\n",
            "\n",
            "Or undo this operation with:\n",
            "\n",
            "  git switch -\n",
            "\n",
            "Turn off this advice by setting config variable advice.detachedHead to false\n",
            "\n",
            "/content/text-generation-webui/repositories/GPTQ-for-LLaMa\n",
            "running install\n",
            "/usr/local/lib/python3.10/dist-packages/setuptools/_distutils/cmd.py:66: SetuptoolsDeprecationWarning: setup.py install is deprecated.\n",
            "!!\n",
            "\n",
            "        ********************************************************************************\n",
            "        Please avoid running ``setup.py`` directly.\n",
            "        Instead, use pypa/build, pypa/installer, pypa/build or\n",
            "        other standards-based tools.\n",
            "\n",
            "        See https://blog.ganssle.io/articles/2021/10/setup-py-deprecated.html for details.\n",
            "        ********************************************************************************\n",
            "\n",
            "!!\n",
            "  self.initialize_options()\n",
            "/usr/local/lib/python3.10/dist-packages/setuptools/_distutils/cmd.py:66: EasyInstallDeprecationWarning: easy_install command is deprecated.\n",
            "!!\n",
            "\n",
            "        ********************************************************************************\n",
            "        Please avoid running ``setup.py`` and ``easy_install``.\n",
            "        Instead, use pypa/build, pypa/installer, pypa/build or\n",
            "        other standards-based tools.\n",
            "\n",
            "        See https://github.com/pypa/setuptools/issues/917 for details.\n",
            "        ********************************************************************************\n",
            "\n",
            "!!\n",
            "  self.initialize_options()\n",
            "running bdist_egg\n",
            "running egg_info\n",
            "creating quant_cuda.egg-info\n",
            "writing quant_cuda.egg-info/PKG-INFO\n",
            "writing dependency_links to quant_cuda.egg-info/dependency_links.txt\n",
            "writing top-level names to quant_cuda.egg-info/top_level.txt\n",
            "writing manifest file 'quant_cuda.egg-info/SOURCES.txt'\n",
            "/usr/local/lib/python3.10/dist-packages/torch/utils/cpp_extension.py:476: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend.\n",
            "  warnings.warn(msg.format('we could not find ninja.'))\n",
            "reading manifest file 'quant_cuda.egg-info/SOURCES.txt'\n",
            "writing manifest file 'quant_cuda.egg-info/SOURCES.txt'\n",
            "installing library code to build/bdist.linux-x86_64/egg\n",
            "running install_lib\n",
            "running build_ext\n",
            "/usr/local/lib/python3.10/dist-packages/torch/utils/cpp_extension.py:398: UserWarning: There are no x86_64-linux-gnu-g++ version bounds defined for CUDA version 11.8\n",
            "  warnings.warn(f'There are no {compiler_name} version bounds defined for CUDA version {cuda_str_version}')\n",
            "building 'quant_cuda' extension\n",
            "creating build\n",
            "creating build/temp.linux-x86_64-cpython-310\n",
            "x86_64-linux-gnu-gcc -pthread -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O2 -Wall -g -fstack-protector-strong -Wformat -Werror=format-security -g -fwrapv -O2 -fPIC -I/usr/local/lib/python3.10/dist-packages/torch/include -I/usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.10/dist-packages/torch/include/TH -I/usr/local/lib/python3.10/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.10 -c quant_cuda.cpp -o build/temp.linux-x86_64-cpython-310/quant_cuda.o -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\\\"_gcc\\\" -DPYBIND11_STDLIB=\\\"_libstdcpp\\\" -DPYBIND11_BUILD_ABI=\\\"_cxxabi1011\\\" -DTORCH_EXTENSION_NAME=quant_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++17\n",
            "/usr/local/cuda/bin/nvcc -I/usr/local/lib/python3.10/dist-packages/torch/include -I/usr/local/lib/python3.10/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/lib/python3.10/dist-packages/torch/include/TH -I/usr/local/lib/python3.10/dist-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/include/python3.10 -c quant_cuda_kernel.cu -o build/temp.linux-x86_64-cpython-310/quant_cuda_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\\\"_gcc\\\" -DPYBIND11_STDLIB=\\\"_libstdcpp\\\" -DPYBIND11_BUILD_ABI=\\\"_cxxabi1011\\\" -DTORCH_EXTENSION_NAME=quant_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=compute_75 -gencode=arch=compute_75,code=sm_75 -std=c++17\n",
            "\u001b[01m\u001b[0m\u001b[01m/usr/local/lib/python3.10/dist-packages/torch/include/c10/util/irange.h(54)\u001b[0m: \u001b[01;35mwarning\u001b[0m #186-D: pointless comparison of unsigned integer with zero\n",
            "          detected during:\n",
            "            instantiation of \u001b[01m\"__nv_bool c10::detail::integer_iterator<I, one_sided, <unnamed>>::operator==(const c10::detail::integer_iterator<I, one_sided, <unnamed>> &) const [with I=size_t, one_sided=false, <unnamed>=0]\"\u001b[0m \u001b[32m\n",
            "(61): here\u001b[0m\n",
            "            instantiation of \u001b[01m\"__nv_bool c10::detail::integer_iterator<I, one_sided, <unnamed>>::operator!=(const c10::detail::integer_iterator<I, one_sided, <unnamed>> &) const [with I=size_t, one_sided=false, <unnamed>=0]\"\u001b[0m \u001b[32m\n",
            "/usr/local/lib/python3.10/dist-packages/torch/include/c10/core/TensorImpl.h(77): here\u001b[0m\n",
            "\n",
            "\u001b[01m\u001b[0m\u001b[01m/usr/local/lib/python3.10/dist-packages/torch/include/c10/util/irange.h(54)\u001b[0m: \u001b[01;35mwarning\u001b[0m #186-D: pointless comparison of unsigned integer with zero\n",
            "          detected during:\n",
            "            instantiation of \u001b[01m\"__nv_bool c10::detail::integer_iterator<I, one_sided, <unnamed>>::operator==(const c10::detail::integer_iterator<I, one_sided, <unnamed>> &) const [with I=std::size_t, one_sided=true, <unnamed>=0]\"\u001b[0m \u001b[32m\n",
            "(61): here\u001b[0m\n",
            "            instantiation of \u001b[01m\"__nv_bool c10::detail::integer_iterator<I, one_sided, <unnamed>>::operator!=(const c10::detail::integer_iterator<I, one_sided, <unnamed>> &) const [with I=std::size_t, one_sided=true, <unnamed>=0]\"\u001b[0m \u001b[32m\n",
            "/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/qualified_name.h(73): here\u001b[0m\n",
            "\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:41:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                         \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:222:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  222 | \u001b[01;36m\u001b[K  De\u001b[m\u001b[KprecatedTypeProperties & type() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:163:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/Dispatch.h:122:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  122 | \u001b[01;36m\u001b[Kinline at::\u001b[m\u001b[KScalarType scalar_type(const at::DeprecatedTypeProperties& t) {\n",
            "      | \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:163:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/Dispatch.h:122:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  122 | \u001b[01;36m\u001b[Kinline at::\u001b[m\u001b[KScalarType scalar_type(const at::DeprecatedTypeProperties& t) {\n",
            "      | \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:1011:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:1032:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:1056:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:1083:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:1106:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:1999:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:2020:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:2043:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:2069:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:166:2092:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  166 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:41:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                         \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:222:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  222 | \u001b[01;36m\u001b[K  De\u001b[m\u001b[KprecatedTypeProperties & type() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:163:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/Dispatch.h:122:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  122 | \u001b[01;36m\u001b[Kinline at::\u001b[m\u001b[KScalarType scalar_type(const at::DeprecatedTypeProperties& t) {\n",
            "      | \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:163:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/Dispatch.h:122:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  122 | \u001b[01;36m\u001b[Kinline at::\u001b[m\u001b[KScalarType scalar_type(const at::DeprecatedTypeProperties& t) {\n",
            "      | \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:1011:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:1032:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:1056:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:1083:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:1106:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:1999:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:2020:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:2043:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:2069:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:261:2092:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  261 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:41:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                         \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:222:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  222 | \u001b[01;36m\u001b[K  De\u001b[m\u001b[KprecatedTypeProperties & type() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:163:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/Dispatch.h:122:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  122 | \u001b[01;36m\u001b[Kinline at::\u001b[m\u001b[KScalarType scalar_type(const at::DeprecatedTypeProperties& t) {\n",
            "      | \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:163:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/Dispatch.h:122:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  122 | \u001b[01;36m\u001b[Kinline at::\u001b[m\u001b[KScalarType scalar_type(const at::DeprecatedTypeProperties& t) {\n",
            "      | \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:1011:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:1032:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:1056:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:1083:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:1106:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:1999:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:2020:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:2043:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:2069:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:420:2092:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  420 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:41:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kat::DeprecatedTypeProperties& at::Tensor::type() const\u001b[m\u001b[K’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                         \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:222:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  222 | \u001b[01;36m\u001b[K  De\u001b[m\u001b[KprecatedTypeProperties & type() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:163:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/Dispatch.h:122:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  122 | \u001b[01;36m\u001b[Kinline at::\u001b[m\u001b[KScalarType scalar_type(const at::DeprecatedTypeProperties& t) {\n",
            "      | \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:163:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[Kc10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)\u001b[m\u001b[K’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/Dispatch.h:122:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  122 | \u001b[01;36m\u001b[Kinline at::\u001b[m\u001b[KScalarType scalar_type(const at::DeprecatedTypeProperties& t) {\n",
            "      | \u001b[01;36m\u001b[K^~~~~~~~~~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:1011:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:1032:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:1056:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:1083:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = double]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:1106:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:\u001b[m\u001b[K In lambda function:\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:1999:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:2020:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:2043:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:2069:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = float]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[Kquant_cuda_kernel.cu:507:2092:\u001b[m\u001b[K \u001b[01;35m\u001b[Kwarning: \u001b[m\u001b[K‘\u001b[01m\u001b[KT* at::Tensor::data() const [with T = int]\u001b[m\u001b[K’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [\u001b[01;35m\u001b[K-Wdeprecated-declarations\u001b[m\u001b[K]\n",
            "  507 |   AT_DISPATCH_FLOATING_TYPES(\n",
            "      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            \u001b[01;35m\u001b[K^\u001b[m\u001b[K\n",
            "\u001b[01m\u001b[K/usr/local/lib/python3.10/dist-packages/torch/include/ATen/core/TensorBody.h:244:1:\u001b[m\u001b[K \u001b[01;36m\u001b[Knote: \u001b[m\u001b[Kdeclared here\n",
            "  244 | \u001b[01;36m\u001b[K  T \u001b[m\u001b[K* data() const {\n",
            "      | \u001b[01;36m\u001b[K^\u001b[m\u001b[K \u001b[01;36m\u001b[K~~\u001b[m\u001b[K\n",
            "creating build/lib.linux-x86_64-cpython-310\n",
            "x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -g -fwrapv -O2 build/temp.linux-x86_64-cpython-310/quant_cuda.o build/temp.linux-x86_64-cpython-310/quant_cuda_kernel.o -L/usr/local/lib/python3.10/dist-packages/torch/lib -L/usr/local/cuda/lib64 -L/usr/lib/x86_64-linux-gnu -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-cpython-310/quant_cuda.cpython-310-x86_64-linux-gnu.so\n",
            "creating build/bdist.linux-x86_64\n",
            "creating build/bdist.linux-x86_64/egg\n",
            "copying build/lib.linux-x86_64-cpython-310/quant_cuda.cpython-310-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg\n",
            "creating stub loader for quant_cuda.cpython-310-x86_64-linux-gnu.so\n",
            "byte-compiling build/bdist.linux-x86_64/egg/quant_cuda.py to quant_cuda.cpython-310.pyc\n",
            "creating build/bdist.linux-x86_64/egg/EGG-INFO\n",
            "copying quant_cuda.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO\n",
            "copying quant_cuda.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n",
            "copying quant_cuda.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n",
            "copying quant_cuda.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO\n",
            "writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt\n",
            "zip_safe flag not set; analyzing archive contents...\n",
            "__pycache__.quant_cuda.cpython-310: module references __file__\n",
            "creating dist\n",
            "creating 'dist/quant_cuda-0.0.0-py3.10-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it\n",
            "removing 'build/bdist.linux-x86_64/egg' (and everything under it)\n",
            "Processing quant_cuda-0.0.0-py3.10-linux-x86_64.egg\n",
            "creating /usr/local/lib/python3.10/dist-packages/quant_cuda-0.0.0-py3.10-linux-x86_64.egg\n",
            "Extracting quant_cuda-0.0.0-py3.10-linux-x86_64.egg to /usr/local/lib/python3.10/dist-packages\n",
            "Adding quant-cuda 0.0.0 to easy-install.pth file\n",
            "\n",
            "Installed /usr/local/lib/python3.10/dist-packages/quant_cuda-0.0.0-py3.10-linux-x86_64.egg\n",
            "Processing dependencies for quant-cuda==0.0.0\n",
            "Finished processing dependencies for quant-cuda==0.0.0\n",
            "\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "626be7|\u001b[1;32mOK\u001b[0m  |   111KiB/s|/content/text-generation-webui/models/13B-HyperMantis_GPTQ/config.json\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "ef1a2b|\u001b[1;32mOK\u001b[0m  |    32KiB/s|/content/text-generation-webui/models/13B-HyperMantis_GPTQ/generation_config.json\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "9c2825|\u001b[1;32mOK\u001b[0m  |   100KiB/s|/content/text-generation-webui/models/13B-HyperMantis_GPTQ/special_tokens_map.json\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "bd7df6|\u001b[1;32mOK\u001b[0m  |    39MiB/s|/content/text-generation-webui/models/13B-HyperMantis_GPTQ/tokenizer.model\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "1a5f99|\u001b[1;32mOK\u001b[0m  |   177KiB/s|/content/text-generation-webui/models/13B-HyperMantis_GPTQ/tokenizer_config.json\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "\u001b[0m\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "c6188d|\u001b[1;32mOK\u001b[0m  |   191MiB/s|/content/text-generation-webui/models/13B-HyperMantis_GPTQ/4bit-128g.safetensors\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "/content/text-generation-webui\n",
            "WARNING:\u001b[33mThe gradio \"share link\" feature downloads a proprietary and unaudited blob to create a reverse tunnel. This is potentially dangerous.\u001b[0m\n",
            "2023-06-03 16:02:54.778494: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
            "bin /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so\n",
            "INFO:\u001b[32mLoading 13B-HyperMantis_GPTQ...\u001b[0m\n",
            "INFO:\u001b[32mFound the following quantized model: models/13B-HyperMantis_GPTQ/4bit-128g.safetensors\u001b[0m\n",
            "INFO:\u001b[32mLoaded the model in 48.04 seconds.\n",
            "\u001b[0m\n",
            "INFO:\u001b[32mLoading the extension \"gallery\"...\u001b[0m\n",
            "Running on local URL:  http://127.0.0.1:7860\n",
            "Running on public URL: https://ab20c6cddce4c53878.gradio.live\n",
            "\n",
            "This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces\n",
            "Output generated in 14.91 seconds (5.37 tokens/s, 80 tokens, context 69, seed 1213300504)\n",
            "Output generated in 4.96 seconds (4.24 tokens/s, 21 tokens, context 59, seed 746554618)\n",
            "Output generated in 14.22 seconds (6.82 tokens/s, 97 tokens, context 109, seed 82452338)\n",
            "Output generated in 22.06 seconds (9.02 tokens/s, 199 tokens, context 88, seed 1850190464)\n",
            "Output generated in 6.35 seconds (8.51 tokens/s, 54 tokens, context 287, seed 184082808)\n",
            "Output generated in 18.68 seconds (8.73 tokens/s, 163 tokens, context 89, seed 182312016)\n",
            "Output generated in 6.59 seconds (2.88 tokens/s, 19 tokens, context 83, seed 227578961)\n",
            "Output generated in 5.09 seconds (1.96 tokens/s, 10 tokens, context 70, seed 765909900)\n",
            "Output generated in 5.15 seconds (0.78 tokens/s, 4 tokens, context 77, seed 1140154390)\n",
            "Output generated in 4.22 seconds (1.18 tokens/s, 5 tokens, context 57, seed 1516374884)\n",
            "Output generated in 4.54 seconds (4.18 tokens/s, 19 tokens, context 46, seed 1781276613)\n",
            "Output generated in 8.31 seconds (5.17 tokens/s, 43 tokens, context 84, seed 2083062902)\n",
            "Output generated in 4.28 seconds (2.57 tokens/s, 11 tokens, context 54, seed 2057072)\n",
            "Output generated in 3.62 seconds (3.59 tokens/s, 13 tokens, context 213, seed 597312006)\n",
            "Output generated in 4.57 seconds (5.69 tokens/s, 26 tokens, context 341, seed 1794745757)\n",
            "Output generated in 4.79 seconds (5.22 tokens/s, 25 tokens, context 45, seed 1297425536)\n",
            "Output generated in 12.13 seconds (5.20 tokens/s, 63 tokens, context 122, seed 1792405316)\n",
            "Output generated in 19.04 seconds (10.45 tokens/s, 199 tokens, context 204, seed 1667089637)\n",
            "Output generated in 19.60 seconds (10.15 tokens/s, 199 tokens, context 403, seed 151529644)\n",
            "Output generated in 6.95 seconds (6.91 tokens/s, 48 tokens, context 602, seed 1798066172)\n",
            "Error in sys.excepthook:\n",
            "Traceback (most recent call last):\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/rich/console.py\", line 1699, in print\n",
            "    extend(render(renderable, render_options))\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/rich/console.py\", line 1331, in render\n",
            "    for render_output in iter_render:\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/rich/traceback.py\", line 520, in __rich_console__\n",
            "    self._render_stack(stack),\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/rich/console.py\", line 510, in _replace\n",
            "    return Group(*renderables, fit=fit)\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/rich/traceback.py\", line 658, in _render_stack\n",
            "    text = Text.assemble(\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/rich/text.py\", line 377, in assemble\n",
            "    append(*part)\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/rich/text.py\", line 931, in append\n",
            "    sanitized_text = strip_control_codes(text)\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/rich/control.py\", line 198, in strip_control_codes\n",
            "    return text.translate(_translate_table)\n",
            "KeyboardInterrupt\n",
            "\n",
            "Original exception was:\n",
            "Traceback (most recent call last):\n",
            "  File \"/content/text-generation-webui/server.py\", line 1081, in <module>\n",
            "    time.sleep(0.5)\n",
            "KeyboardInterrupt\n",
            "Killing tunnel 127.0.0.1:7860 <> https://ab20c6cddce4c53878.gradio.live\n",
            "^C\n"
          ]
        }
      ],
      "source": [
        "%cd /content\n",
        "!apt-get -y install -qq aria2\n",
        "\n",
        "!git clone -b V1.0 https://github.com/Troyanovsky/text-generation-webui\n",
        "%cd /content/text-generation-webui\n",
        "!pip install -r requirements.txt\n",
        "!pip install -U gradio==3.32.0\n",
        "\n",
        "!mkdir /content/text-generation-webui/repositories\n",
        "%cd /content/text-generation-webui/repositories\n",
        "!git clone -b V1.0 https://github.com/Troyanovsky/GPTQ-for-LLaMa\n",
        "%cd GPTQ-for-LLaMa\n",
        "!python setup_cuda.py install\n",
        "\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/digitous/13B-HyperMantis_GPTQ_4bit-128g/resolve/main/config.json -d /content/text-generation-webui/models/13B-HyperMantis_GPTQ -o config.json\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/digitous/13B-HyperMantis_GPTQ_4bit-128g/resolve/main/generation_config.json -d /content/text-generation-webui/models/13B-HyperMantis_GPTQ -o generation_config.json\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/digitous/13B-HyperMantis_GPTQ_4bit-128g/resolve/main/special_tokens_map.json -d /content/text-generation-webui/models/13B-HyperMantis_GPTQ -o special_tokens_map.json\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/digitous/13B-HyperMantis_GPTQ_4bit-128g/resolve/main/tokenizer.model -d /content/text-generation-webui/models/13B-HyperMantis_GPTQ -o tokenizer.model\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/digitous/13B-HyperMantis_GPTQ_4bit-128g/resolve/main/tokenizer_config.json -d /content/text-generation-webui/models/13B-HyperMantis_GPTQ -o tokenizer_config.json\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/digitous/13B-HyperMantis_GPTQ_4bit-128g/resolve/main/4bit-128g.safetensors -d /content/text-generation-webui/models/13B-HyperMantis_GPTQ -o 4bit-128g.safetensors\n",
        "\n",
        "%cd /content/text-generation-webui\n",
        "!python server.py --share --chat --wbits 4 --groupsize 128 --model_type llama\n",
        "    "
      ]
    }
  ]
}