Kuchiki_1_1_L2_7B_GGUF.ipynb

{
  "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-Colab-UI/blob/main/Kuchiki_1_1_L2_7B_GGUF.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XNkpBtLvuTOp"
      },
      "source": [
        "## Kuchiki-1.1-L2-7B-GGUF 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: Alpaca-InstructOnly\n",
        "\n",
        "```\n",
        "### Instruction:\n",
        "\n",
        "{prompt}\n",
        "\n",
        "### Response:\n",
        "```"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "D-MiHp_bveP6",
        "outputId": "455ced9e-013f-4b23-bad1-fd4f7f3d266b"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content\n",
            "Selecting previously unselected package libc-ares2:amd64.\n",
            "(Reading database ... 120895 files and directories currently installed.)\n",
            "Preparing to unpack .../libc-ares2_1.18.1-1ubuntu0.22.04.2_amd64.deb ...\n",
            "Unpacking libc-ares2:amd64 (1.18.1-1ubuntu0.22.04.2) ...\n",
            "Selecting previously unselected package libaria2-0:amd64.\n",
            "Preparing to unpack .../libaria2-0_1.36.0-1_amd64.deb ...\n",
            "Unpacking libaria2-0:amd64 (1.36.0-1) ...\n",
            "Selecting previously unselected package aria2.\n",
            "Preparing to unpack .../aria2_1.36.0-1_amd64.deb ...\n",
            "Unpacking aria2 (1.36.0-1) ...\n",
            "Setting up libc-ares2:amd64 (1.18.1-1ubuntu0.22.04.2) ...\n",
            "Setting up libaria2-0:amd64 (1.36.0-1) ...\n",
            "Setting up aria2 (1.36.0-1) ...\n",
            "Processing triggers for man-db (2.10.2-1) ...\n",
            "Processing triggers for libc-bin (2.35-0ubuntu3.1) ...\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_5.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_0.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc_proxy.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbb.so.12 is not a symbolic link\n",
            "\n",
            "Cloning into 'text-generation-webui'...\n",
            "remote: Enumerating objects: 10842, done.\u001b[K\n",
            "remote: Counting objects: 100% (1142/1142), done.\u001b[K\n",
            "remote: Compressing objects: 100% (88/88), done.\u001b[K\n",
            "remote: Total 10842 (delta 1085), reused 1054 (delta 1054), pack-reused 9700\u001b[K\n",
            "Receiving objects: 100% (10842/10842), 3.53 MiB | 3.54 MiB/s, done.\n",
            "Resolving deltas: 100% (7419/7419), done.\n",
            "Note: switching to '7d3a0b5387d4de8bb9412d285092fb232ed83b19'.\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",
            "Ignoring bitsandbytes: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Ignoring auto-gptq: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Collecting auto-gptq==0.4.2+cu117 (from -r requirements.txt (line 31))\n",
            "  Downloading https://github.com/PanQiWei/AutoGPTQ/releases/download/v0.4.2/auto_gptq-0.4.2+cu117-cp310-cp310-linux_x86_64.whl (1.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m16.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring exllama: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Collecting exllama==0.0.10+cu117 (from -r requirements.txt (line 35))\n",
            "  Downloading https://github.com/jllllll/exllama/releases/download/0.0.10/exllama-0.0.10+cu117-cp310-cp310-linux_x86_64.whl (355 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m355.2/355.2 kB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring llama-cpp-python: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Collecting llama-cpp-python-cuda==0.1.81+cu117 (from -r requirements.txt (line 43))\n",
            "  Downloading https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.1.81+cu117-cp310-cp310-linux_x86_64.whl (12.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.8/12.8 MB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring llama-cpp-python-ggml: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Collecting llama-cpp-python-ggml==0.1.78+cpuavx2 (from -r requirements.txt (line 47))\n",
            "  Downloading https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python_ggml-0.1.78+cpuavx2-cp310-cp310-linux_x86_64.whl (731 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.6/731.6 kB\u001b[0m \u001b[31m25.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring llama-cpp-python-ggml-cuda: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Collecting llama-cpp-python-ggml-cuda==0.1.78+cu117 (from -r requirements.txt (line 49))\n",
            "  Downloading https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_ggml_cuda-0.1.78+cu117-cp310-cp310-linux_x86_64.whl (12.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.4/12.4 MB\u001b[0m \u001b[31m18.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring gptq-for-llama: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Collecting gptq-for-llama==0.1.0+cu117 (from -r requirements.txt (line 53))\n",
            "  Downloading https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.0/gptq_for_llama-0.1.0+cu117-cp310-cp310-linux_x86_64.whl (732 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m732.9/732.9 kB\u001b[0m \u001b[31m32.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting ctransformers==0.2.24+cu117 (from -r requirements.txt (line 56))\n",
            "  Downloading https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.24+cu117-py3-none-any.whl (15.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.1/15.1 MB\u001b[0m \u001b[31m18.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting aiofiles==23.1.0 (from -r requirements.txt (line 1))\n",
            "  Downloading aiofiles-23.1.0-py3-none-any.whl (14 kB)\n",
            "Collecting fastapi==0.95.2 (from -r requirements.txt (line 2))\n",
            "  Downloading fastapi-0.95.2-py3-none-any.whl (56 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.0/57.0 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting gradio_client==0.2.5 (from -r requirements.txt (line 3))\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[31m19.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting gradio==3.33.1 (from -r requirements.txt (line 4))\n",
            "  Downloading gradio-3.33.1-py3-none-any.whl (20.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m20.0/20.0 MB\u001b[0m \u001b[31m80.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting accelerate==0.21.* (from -r requirements.txt (line 6))\n",
            "  Downloading accelerate-0.21.0-py3-none-any.whl (244 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m244.2/244.2 kB\u001b[0m \u001b[31m27.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting colorama (from -r requirements.txt (line 7))\n",
            "  Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
            "Collecting datasets (from -r requirements.txt (line 8))\n",
            "  Downloading datasets-2.14.5-py3-none-any.whl (519 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m519.6/519.6 kB\u001b[0m \u001b[31m50.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting einops (from -r requirements.txt (line 9))\n",
            "  Downloading einops-0.6.1-py3-none-any.whl (42 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.2/42.2 kB\u001b[0m \u001b[31m4.9 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 10)) (3.4.4)\n",
            "Collecting numpy==1.24 (from -r requirements.txt (line 11))\n",
            "  Downloading numpy-1.24.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.3/17.3 MB\u001b[0m \u001b[31m16.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 12)) (1.5.3)\n",
            "Collecting peft==0.5.* (from -r requirements.txt (line 13))\n",
            "  Downloading peft-0.5.0-py3-none-any.whl (85 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.6/85.6 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting Pillow>=9.5.0 (from -r requirements.txt (line 14))\n",
            "  Downloading Pillow-10.0.1-cp310-cp310-manylinux_2_28_x86_64.whl (3.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m94.7 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 15)) (6.0.1)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 16)) (2.31.0)\n",
            "Collecting safetensors==0.3.2 (from -r requirements.txt (line 17))\n",
            "  Downloading safetensors-0.3.2-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[31m74.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting transformers==4.32.* (from -r requirements.txt (line 18))\n",
            "  Downloading transformers-4.32.1-py3-none-any.whl (7.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.5/7.5 MB\u001b[0m \u001b[31m111.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 19)) (1.11.2)\n",
            "Collecting sentencepiece (from -r requirements.txt (line 20))\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[31m84.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: tensorboard in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 21)) (2.13.0)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 22)) (4.66.1)\n",
            "Collecting wandb (from -r requirements.txt (line 23))\n",
            "  Downloading wandb-0.15.10-py3-none-any.whl (2.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m89.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting bitsandbytes==0.41.1 (from -r requirements.txt (line 26))\n",
            "  Downloading bitsandbytes-0.41.1-py3-none-any.whl (92.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.6/92.6 MB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting llama-cpp-python==0.1.81 (from -r requirements.txt (line 38))\n",
            "  Downloading llama_cpp_python-0.1.81.tar.gz (1.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m95.3 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: pydantic!=1.7,!=1.7.1,!=1.7.2,!=1.7.3,!=1.8,!=1.8.1,<2.0.0,>=1.6.2 in /usr/local/lib/python3.10/dist-packages (from fastapi==0.95.2->-r requirements.txt (line 2)) (1.10.12)\n",
            "Collecting starlette<0.28.0,>=0.27.0 (from fastapi==0.95.2->-r requirements.txt (line 2))\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[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio_client==0.2.5->-r requirements.txt (line 3)) (2023.6.0)\n",
            "Collecting httpx (from gradio_client==0.2.5->-r requirements.txt (line 3))\n",
            "  Downloading httpx-0.25.0-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.7/75.7 kB\u001b[0m \u001b[31m9.4 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 3))\n",
            "  Downloading huggingface_hub-0.17.2-py3-none-any.whl (294 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m294.9/294.9 kB\u001b[0m \u001b[31m32.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio_client==0.2.5->-r requirements.txt (line 3)) (23.1)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from gradio_client==0.2.5->-r requirements.txt (line 3)) (4.5.0)\n",
            "Collecting websockets (from gradio_client==0.2.5->-r requirements.txt (line 3))\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[31m17.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1->-r requirements.txt (line 4)) (3.8.5)\n",
            "Requirement already satisfied: altair>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1->-r requirements.txt (line 4)) (4.2.2)\n",
            "Collecting ffmpy (from gradio==3.33.1->-r requirements.txt (line 4))\n",
            "  Downloading ffmpy-0.3.1.tar.gz (5.5 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==3.33.1->-r requirements.txt (line 4)) (3.1.2)\n",
            "Requirement already satisfied: markdown-it-py[linkify]>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1->-r requirements.txt (line 4)) (3.0.0)\n",
            "Requirement already satisfied: markupsafe in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1->-r requirements.txt (line 4)) (2.1.3)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1->-r requirements.txt (line 4)) (3.7.1)\n",
            "Collecting mdit-py-plugins<=0.3.3 (from gradio==3.33.1->-r requirements.txt (line 4))\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[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting orjson (from gradio==3.33.1->-r requirements.txt (line 4))\n",
            "  Downloading orjson-3.9.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (138 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m138.7/138.7 kB\u001b[0m \u001b[31m16.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pydub (from gradio==3.33.1->-r requirements.txt (line 4))\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==3.33.1->-r requirements.txt (line 4)) (2.16.1)\n",
            "Collecting python-multipart (from gradio==3.33.1->-r requirements.txt (line 4))\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[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting semantic-version (from gradio==3.33.1->-r requirements.txt (line 4))\n",
            "  Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
            "Collecting uvicorn>=0.14.0 (from gradio==3.33.1->-r requirements.txt (line 4))\n",
            "  Downloading uvicorn-0.23.2-py3-none-any.whl (59 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.5/59.5 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate==0.21.*->-r requirements.txt (line 6)) (5.9.5)\n",
            "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.21.*->-r requirements.txt (line 6)) (2.0.1+cu118)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.32.*->-r requirements.txt (line 18)) (3.12.2)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.32.*->-r requirements.txt (line 18)) (2023.6.3)\n",
            "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers==4.32.*->-r requirements.txt (line 18))\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[31m119.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting diskcache>=5.6.1 (from llama-cpp-python==0.1.81->-r requirements.txt (line 38))\n",
            "  Downloading diskcache-5.6.3-py3-none-any.whl (45 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.5/45.5 kB\u001b[0m \u001b[31m4.9 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 8)) (9.0.0)\n",
            "Collecting dill<0.3.8,>=0.3.0 (from datasets->-r requirements.txt (line 8))\n",
            "  Downloading dill-0.3.7-py3-none-any.whl (115 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting xxhash (from datasets->-r requirements.txt (line 8))\n",
            "  Downloading xxhash-3.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting multiprocess (from datasets->-r requirements.txt (line 8))\n",
            "  Downloading multiprocess-0.70.15-py310-none-any.whl (134 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m16.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 12)) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 12)) (2023.3.post1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 16)) (3.2.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 16)) (3.4)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 16)) (2.0.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 16)) (2023.7.22)\n",
            "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (1.4.0)\n",
            "Requirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (1.57.0)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (2.17.3)\n",
            "Requirement already satisfied: google-auth-oauthlib<1.1,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (1.0.0)\n",
            "Requirement already satisfied: protobuf>=3.19.6 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (3.20.3)\n",
            "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (67.7.2)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (0.7.1)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (2.3.7)\n",
            "Requirement already satisfied: wheel>=0.26 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 21)) (0.41.2)\n",
            "Requirement already satisfied: Click!=8.0.0,>=7.1 in /usr/local/lib/python3.10/dist-packages (from wandb->-r requirements.txt (line 23)) (8.1.7)\n",
            "Collecting GitPython!=3.1.29,>=1.0.0 (from wandb->-r requirements.txt (line 23))\n",
            "  Downloading GitPython-3.1.36-py3-none-any.whl (189 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m189.5/189.5 kB\u001b[0m \u001b[31m21.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting sentry-sdk>=1.0.0 (from wandb->-r requirements.txt (line 23))\n",
            "  Downloading sentry_sdk-1.31.0-py2.py3-none-any.whl (224 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m224.8/224.8 kB\u001b[0m \u001b[31m24.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting docker-pycreds>=0.4.0 (from wandb->-r requirements.txt (line 23))\n",
            "  Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\n",
            "Collecting pathtools (from wandb->-r requirements.txt (line 23))\n",
            "  Downloading pathtools-0.1.2.tar.gz (11 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting setproctitle (from wandb->-r requirements.txt (line 23))\n",
            "  Downloading setproctitle-1.3.2-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30 kB)\n",
            "Requirement already satisfied: appdirs>=1.4.3 in /usr/local/lib/python3.10/dist-packages (from wandb->-r requirements.txt (line 23)) (1.4.4)\n",
            "Collecting rouge (from auto-gptq==0.4.2+cu117->-r requirements.txt (line 31))\n",
            "  Downloading rouge-1.0.1-py3-none-any.whl (13 kB)\n",
            "Requirement already satisfied: py-cpuinfo<10.0.0,>=9.0.0 in /usr/local/lib/python3.10/dist-packages (from ctransformers==0.2.24+cu117->-r requirements.txt (line 56)) (9.0.0)\n",
            "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.33.1->-r requirements.txt (line 4)) (0.4)\n",
            "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.33.1->-r requirements.txt (line 4)) (4.19.0)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.33.1->-r requirements.txt (line 4)) (0.12.0)\n",
            "Requirement already satisfied: six>=1.4.0 in /usr/local/lib/python3.10/dist-packages (from docker-pycreds>=0.4.0->wandb->-r requirements.txt (line 23)) (1.16.0)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1->-r requirements.txt (line 4)) (23.1.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1->-r requirements.txt (line 4)) (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==3.33.1->-r requirements.txt (line 4)) (4.0.3)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1->-r requirements.txt (line 4)) (1.9.2)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1->-r requirements.txt (line 4)) (1.4.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1->-r requirements.txt (line 4)) (1.3.1)\n",
            "Collecting gitdb<5,>=4.0.1 (from GitPython!=3.1.29,>=1.0.0->wandb->-r requirements.txt (line 23))\n",
            "  Downloading gitdb-4.0.10-py3-none-any.whl (62 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 21)) (5.3.1)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 21)) (0.3.0)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 21)) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<1.1,>=0.5->tensorboard->-r requirements.txt (line 21)) (1.3.1)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio==3.33.1->-r requirements.txt (line 4)) (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==3.33.1->-r requirements.txt (line 4)) (2.0.2)\n",
            "INFO: pip is looking at multiple versions of mdit-py-plugins to determine which version is compatible with other requirements. This could take a while.\n",
            "Collecting mdit-py-plugins<=0.3.3 (from gradio==3.33.1->-r requirements.txt (line 4))\n",
            "  Downloading mdit_py_plugins-0.3.2-py3-none-any.whl (50 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.4/50.4 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Downloading mdit_py_plugins-0.3.1-py3-none-any.whl (46 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.5/46.5 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Downloading mdit_py_plugins-0.3.0-py3-none-any.whl (43 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.7/43.7 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Downloading mdit_py_plugins-0.2.8-py3-none-any.whl (41 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.0/41.0 kB\u001b[0m \u001b[31m1.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Downloading mdit_py_plugins-0.2.7-py3-none-any.whl (41 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.0/41.0 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Downloading mdit_py_plugins-0.2.6-py3-none-any.whl (39 kB)\n",
            "  Downloading mdit_py_plugins-0.2.5-py3-none-any.whl (39 kB)\n",
            "INFO: pip is looking at multiple versions of mdit-py-plugins to determine which version is compatible with other requirements. This could take a while.\n",
            "  Downloading mdit_py_plugins-0.2.4-py3-none-any.whl (39 kB)\n",
            "  Downloading mdit_py_plugins-0.2.3-py3-none-any.whl (39 kB)\n",
            "  Downloading mdit_py_plugins-0.2.2-py3-none-any.whl (39 kB)\n",
            "  Downloading mdit_py_plugins-0.2.1-py3-none-any.whl (38 kB)\n",
            "  Downloading mdit_py_plugins-0.2.0-py3-none-any.whl (38 kB)\n",
            "INFO: This is taking longer than usual. You might need to provide the dependency resolver with stricter constraints to reduce runtime. See https://pip.pypa.io/warnings/backtracking for guidance. If you want to abort this run, press Ctrl + C.\n",
            "  Downloading mdit_py_plugins-0.1.0-py3-none-any.whl (37 kB)\n",
            "Collecting markdown-it-py[linkify]>=2.0.0 (from gradio==3.33.1->-r requirements.txt (line 4))\n",
            "  Downloading markdown_it_py-3.0.0-py3-none-any.whl (87 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.5/87.5 kB\u001b[0m \u001b[31m11.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Downloading markdown_it_py-2.2.0-py3-none-any.whl (84 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.5/84.5 kB\u001b[0m \u001b[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: anyio<5,>=3.4.0 in /usr/local/lib/python3.10/dist-packages (from starlette<0.28.0,>=0.27.0->fastapi==0.95.2->-r requirements.txt (line 2)) (3.7.1)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.21.*->-r requirements.txt (line 6)) (1.12)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.21.*->-r requirements.txt (line 6)) (3.1)\n",
            "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.21.*->-r requirements.txt (line 6)) (2.0.0)\n",
            "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.10.0->accelerate==0.21.*->-r requirements.txt (line 6)) (3.27.4.1)\n",
            "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.10.0->accelerate==0.21.*->-r requirements.txt (line 6)) (16.0.6)\n",
            "Collecting h11>=0.8 (from uvicorn>=0.14.0->gradio==3.33.1->-r requirements.txt (line 4))\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[31m7.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting httpcore<0.19.0,>=0.18.0 (from httpx->gradio_client==0.2.5->-r requirements.txt (line 3))\n",
            "  Downloading httpcore-0.18.0-py3-none-any.whl (76 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.0/76.0 kB\u001b[0m \u001b[31m9.6 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 3)) (1.3.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1->-r requirements.txt (line 4)) (1.1.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1->-r requirements.txt (line 4)) (0.11.0)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1->-r requirements.txt (line 4)) (4.42.1)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1->-r requirements.txt (line 4)) (1.4.5)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1->-r requirements.txt (line 4)) (3.1.1)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.4.0->starlette<0.28.0,>=0.27.0->fastapi==0.95.2->-r requirements.txt (line 2)) (1.1.3)\n",
            "Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->GitPython!=3.1.29,>=1.0.0->wandb->-r requirements.txt (line 23))\n",
            "  Downloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
            "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio==3.33.1->-r requirements.txt (line 4)) (2023.7.1)\n",
            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio==3.33.1->-r requirements.txt (line 4)) (0.30.2)\n",
            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio==3.33.1->-r requirements.txt (line 4)) (0.10.2)\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==3.33.1->-r requirements.txt (line 4)) (1.0.2)\n",
            "Requirement already satisfied: pyasn1<0.6.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard->-r requirements.txt (line 21)) (0.5.0)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<1.1,>=0.5->tensorboard->-r requirements.txt (line 21)) (3.2.2)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate==0.21.*->-r requirements.txt (line 6)) (1.3.0)\n",
            "Building wheels for collected packages: llama-cpp-python, ffmpy, pathtools\n",
            "  Building wheel for llama-cpp-python (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for llama-cpp-python: filename=llama_cpp_python-0.1.81-cp310-cp310-linux_x86_64.whl size=409160 sha256=ec8a332df6dff059296c04b96010b72258231fd5c231ba1f536c1dfa48f3ce09\n",
            "  Stored in directory: /root/.cache/pip/wheels/99/27/c0/ccda486d8dc16ebb8c61d9d7959380eced2cb3279cf0145dfe\n",
            "  Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for ffmpy: filename=ffmpy-0.3.1-py3-none-any.whl size=5579 sha256=7c8f9ee04c08025fd6a4bffc0f5fa03e35cd0d4a900ee2e3f713412b9802a692\n",
            "  Stored in directory: /root/.cache/pip/wheels/01/a6/d1/1c0828c304a4283b2c1639a09ad86f83d7c487ef34c6b4a1bf\n",
            "  Building wheel for pathtools (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for pathtools: filename=pathtools-0.1.2-py3-none-any.whl size=8791 sha256=43b150a607df7d46c879183679acca6423cd44303a23b57f613957d9295ac546\n",
            "  Stored in directory: /root/.cache/pip/wheels/e7/f3/22/152153d6eb222ee7a56ff8617d80ee5207207a8c00a7aab794\n",
            "Successfully built llama-cpp-python ffmpy pathtools\n",
            "Installing collected packages: tokenizers, sentencepiece, safetensors, pydub, pathtools, gptq-for-llama, ffmpy, bitsandbytes, xxhash, websockets, smmap, setproctitle, sentry-sdk, semantic-version, rouge, python-multipart, Pillow, orjson, numpy, markdown-it-py, h11, einops, docker-pycreds, diskcache, dill, colorama, aiofiles, uvicorn, starlette, multiprocess, mdit-py-plugins, llama-cpp-python-ggml-cuda, llama-cpp-python-ggml, llama-cpp-python-cuda, llama-cpp-python, huggingface-hub, httpcore, gitdb, transformers, httpx, GitPython, fastapi, ctransformers, wandb, gradio_client, datasets, gradio, accelerate, peft, exllama, auto-gptq\n",
            "  Attempting uninstall: Pillow\n",
            "    Found existing installation: Pillow 9.4.0\n",
            "    Uninstalling Pillow-9.4.0:\n",
            "      Successfully uninstalled Pillow-9.4.0\n",
            "  Attempting uninstall: numpy\n",
            "    Found existing installation: numpy 1.23.5\n",
            "    Uninstalling numpy-1.23.5:\n",
            "      Successfully uninstalled numpy-1.23.5\n",
            "  Attempting uninstall: markdown-it-py\n",
            "    Found existing installation: markdown-it-py 3.0.0\n",
            "    Uninstalling markdown-it-py-3.0.0:\n",
            "      Successfully uninstalled markdown-it-py-3.0.0\n",
            "  Attempting uninstall: mdit-py-plugins\n",
            "    Found existing installation: mdit-py-plugins 0.4.0\n",
            "    Uninstalling mdit-py-plugins-0.4.0:\n",
            "      Successfully uninstalled mdit-py-plugins-0.4.0\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "numba 0.56.4 requires numpy<1.24,>=1.18, but you have numpy 1.24.0 which is incompatible.\n",
            "seaborn 0.12.2 requires numpy!=1.24.0,>=1.17, but you have numpy 1.24.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed GitPython-3.1.36 Pillow-10.0.1 accelerate-0.21.0 aiofiles-23.1.0 auto-gptq-0.4.2+cu117 bitsandbytes-0.41.1 colorama-0.4.6 ctransformers-0.2.24+cu117 datasets-2.14.5 dill-0.3.7 diskcache-5.6.3 docker-pycreds-0.4.0 einops-0.6.1 exllama-0.0.10+cu117 fastapi-0.95.2 ffmpy-0.3.1 gitdb-4.0.10 gptq-for-llama-0.1.0+cu117 gradio-3.33.1 gradio_client-0.2.5 h11-0.14.0 httpcore-0.18.0 httpx-0.25.0 huggingface-hub-0.17.2 llama-cpp-python-0.1.81 llama-cpp-python-cuda-0.1.81+cu117 llama-cpp-python-ggml-0.1.78+cpuavx2 llama-cpp-python-ggml-cuda-0.1.78+cu117 markdown-it-py-2.2.0 mdit-py-plugins-0.3.3 multiprocess-0.70.15 numpy-1.24.0 orjson-3.9.7 pathtools-0.1.2 peft-0.5.0 pydub-0.25.1 python-multipart-0.0.6 rouge-1.0.1 safetensors-0.3.2 semantic-version-2.10.0 sentencepiece-0.1.99 sentry-sdk-1.31.0 setproctitle-1.3.2 smmap-5.0.1 starlette-0.27.0 tokenizers-0.13.3 transformers-4.32.1 uvicorn-0.23.2 wandb-0.15.10 websockets-11.0.3 xxhash-3.3.0\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "PIL",
                  "numpy"
                ]
              }
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: gradio==3.33.1 in /usr/local/lib/python3.10/dist-packages (3.33.1)\n",
            "Requirement already satisfied: aiofiles in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (23.1.0)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (3.8.5)\n",
            "Requirement already satisfied: altair>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (4.2.2)\n",
            "Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.95.2)\n",
            "Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.3.1)\n",
            "Requirement already satisfied: gradio-client>=0.2.4 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.2.5)\n",
            "Requirement already satisfied: httpx in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.25.0)\n",
            "Requirement already satisfied: huggingface-hub>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.17.2)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (3.1.2)\n",
            "Requirement already satisfied: markdown-it-py[linkify]>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (2.2.0)\n",
            "Requirement already satisfied: markupsafe in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (2.1.3)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (3.7.1)\n",
            "Requirement already satisfied: mdit-py-plugins<=0.3.3 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.3.3)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (1.24.0)\n",
            "Requirement already satisfied: orjson in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (3.9.7)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (1.5.3)\n",
            "Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (10.0.1)\n",
            "Requirement already satisfied: pydantic in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (1.10.12)\n",
            "Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.25.1)\n",
            "Requirement already satisfied: pygments>=2.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (2.16.1)\n",
            "Requirement already satisfied: python-multipart in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.0.6)\n",
            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (6.0.1)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (2.31.0)\n",
            "Requirement already satisfied: semantic-version in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (2.10.0)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (4.5.0)\n",
            "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (0.23.2)\n",
            "Requirement already satisfied: websockets>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.33.1) (11.0.3)\n",
            "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.33.1) (0.4)\n",
            "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.33.1) (4.19.0)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair>=4.2.0->gradio==3.33.1) (0.12.0)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client>=0.2.4->gradio==3.33.1) (2023.6.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio-client>=0.2.4->gradio==3.33.1) (23.1)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.0->gradio==3.33.1) (3.12.2)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.0->gradio==3.33.1) (4.66.1)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio==3.33.1) (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==3.33.1) (2.0.2)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->gradio==3.33.1) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->gradio==3.33.1) (2023.3.post1)\n",
            "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio==3.33.1) (8.1.7)\n",
            "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio==3.33.1) (0.14.0)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1) (23.1.0)\n",
            "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1) (3.2.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1) (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==3.33.1) (4.0.3)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1) (1.9.2)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1) (1.4.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->gradio==3.33.1) (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==3.33.1) (0.27.0)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.33.1) (2023.7.22)\n",
            "Requirement already satisfied: httpcore<0.19.0,>=0.18.0 in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.33.1) (0.18.0)\n",
            "Requirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.33.1) (3.4)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.33.1) (1.3.0)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1) (1.1.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1) (0.11.0)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1) (4.42.1)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1) (1.4.5)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->gradio==3.33.1) (3.1.1)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->gradio==3.33.1) (2.0.4)\n",
            "Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from httpcore<0.19.0,>=0.18.0->httpx->gradio==3.33.1) (3.7.1)\n",
            "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio==3.33.1) (2023.7.1)\n",
            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio==3.33.1) (0.30.2)\n",
            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio==3.33.1) (0.10.2)\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==3.33.1) (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==3.33.1) (1.16.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->httpcore<0.19.0,>=0.18.0->httpx->gradio==3.33.1) (1.1.3)\n",
            "Found existing installation: llama-cpp-python 0.1.81\n",
            "Uninstalling llama-cpp-python-0.1.81:\n",
            "  Successfully uninstalled llama-cpp-python-0.1.81\n",
            "Collecting llama-cpp-python\n",
            "  Downloading llama_cpp_python-0.2.6.tar.gz (1.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m23.0 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",
            "  Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python) (4.5.0)\n",
            "Requirement already satisfied: numpy>=1.20.0 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python) (1.24.0)\n",
            "Requirement already satisfied: diskcache>=5.6.1 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python) (5.6.3)\n",
            "Building wheels for collected packages: llama-cpp-python\n",
            "  Building wheel for llama-cpp-python (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for llama-cpp-python: filename=llama_cpp_python-0.2.6-cp310-cp310-manylinux_2_35_x86_64.whl size=6197484 sha256=f4a75e2773dc4adce5ee7e2dbc1a4928c246c36275533f6679c898aa3f294601\n",
            "  Stored in directory: /tmp/pip-ephem-wheel-cache-4ubg_k7h/wheels/6c/ae/75/c2ad88ef0d1e219f981c51367b8533025345d1a14aa2f09662\n",
            "Successfully built llama-cpp-python\n",
            "Installing collected packages: llama-cpp-python\n",
            "Successfully installed llama-cpp-python-0.2.6\n",
            "\u001b[0m\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "37c3c5|\u001b[1;32mOK\u001b[0m  |    83MiB/s|/content/text-generation-webui/models//kuchiki-1.1-l2-7b.Q5_K_M.gguf\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "/content/text-generation-webui\n",
            "2023-09-21 07:20:18 WARNING:\u001b[33mThe gradio \"share link\" feature uses a proprietary executable to create a reverse tunnel. Use it with care.\u001b[0m\n",
            "2023-09-21 07:20:27.502047: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
            "2023-09-21 07:20:29 INFO:\u001b[32mLoading kuchiki-1.1-l2-7b.Q5_K_M.gguf...\u001b[0m\n",
            "ggml_init_cublas: found 1 CUDA devices:\n",
            "  Device 0: Tesla T4, compute capability 7.5\n",
            "ggml_init_cublas: found 1 CUDA devices:\n",
            "  Device 0: Tesla T4, compute capability 7.5\n",
            "2023-09-21 07:20:41 INFO:\u001b[32mllama.cpp weights detected: models/kuchiki-1.1-l2-7b.Q5_K_M.gguf\u001b[0m\n",
            "2023-09-21 07:20:41 INFO:\u001b[32mCache capacity is 0 bytes\u001b[0m\n",
            "llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from models/kuchiki-1.1-l2-7b.Q5_K_M.gguf (version GGUF V2 (latest))\n",
            "llama_model_loader: - tensor    0:                token_embd.weight q5_K     [  4096, 32000,     1,     1 ]\n",
            "llama_model_loader: - tensor    1:              blk.0.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    2:              blk.0.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    3:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    4:         blk.0.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    5:            blk.0.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor    6:              blk.0.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor    7:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    8:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor    9:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   10:              blk.1.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   11:              blk.1.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   12:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   13:         blk.1.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   14:            blk.1.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   15:              blk.1.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   16:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   17:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   18:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   19:              blk.2.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   20:              blk.2.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   21:              blk.2.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   22:         blk.2.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   23:            blk.2.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   24:              blk.2.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   25:            blk.2.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   26:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   27:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   28:              blk.3.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   29:              blk.3.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   30:              blk.3.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   31:         blk.3.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   32:            blk.3.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   33:              blk.3.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   34:            blk.3.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   35:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   36:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   37:              blk.4.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   38:              blk.4.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   39:              blk.4.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   40:         blk.4.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   41:            blk.4.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   42:              blk.4.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   43:            blk.4.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   44:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   45:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   46:              blk.5.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   47:              blk.5.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   48:              blk.5.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   49:         blk.5.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   50:            blk.5.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   51:              blk.5.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   52:            blk.5.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   53:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   54:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   55:              blk.6.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   56:              blk.6.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   57:              blk.6.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   58:         blk.6.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   59:            blk.6.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   60:              blk.6.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   61:            blk.6.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   62:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   63:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   64:              blk.7.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   65:              blk.7.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   66:              blk.7.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   67:         blk.7.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   68:            blk.7.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   69:              blk.7.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   70:            blk.7.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   71:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   72:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   73:              blk.8.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   74:              blk.8.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   75:              blk.8.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   76:         blk.8.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   77:            blk.8.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   78:              blk.8.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   79:            blk.8.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   80:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   81:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   82:              blk.9.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   83:              blk.9.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   84:              blk.9.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   85:         blk.9.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   86:            blk.9.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   87:              blk.9.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   88:            blk.9.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   89:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   90:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   91:             blk.10.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   92:             blk.10.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   93:             blk.10.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   94:        blk.10.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   95:           blk.10.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   96:             blk.10.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   97:           blk.10.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   98:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   99:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  100:             blk.11.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  101:             blk.11.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  102:             blk.11.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  103:        blk.11.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  104:           blk.11.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  105:             blk.11.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  106:           blk.11.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  107:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  108:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  109:             blk.12.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  110:             blk.12.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  111:             blk.12.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  112:        blk.12.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  113:           blk.12.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  114:             blk.12.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  115:           blk.12.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  116:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  117:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  118:             blk.13.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  119:             blk.13.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  120:             blk.13.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  121:        blk.13.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  122:           blk.13.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  123:             blk.13.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  124:           blk.13.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  125:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  126:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  127:             blk.14.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  128:             blk.14.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  129:             blk.14.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  130:        blk.14.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  131:           blk.14.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  132:             blk.14.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  133:           blk.14.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  134:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  135:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  136:             blk.15.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  137:             blk.15.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  138:             blk.15.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  139:        blk.15.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  140:           blk.15.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  141:             blk.15.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  142:           blk.15.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  143:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  144:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  145:             blk.16.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  146:             blk.16.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  147:             blk.16.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  148:        blk.16.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  149:           blk.16.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  150:             blk.16.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  151:           blk.16.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  152:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  153:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  154:             blk.17.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  155:             blk.17.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  156:             blk.17.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  157:        blk.17.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  158:           blk.17.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  159:             blk.17.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  160:           blk.17.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  161:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  162:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  163:             blk.18.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  164:             blk.18.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  165:             blk.18.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  166:        blk.18.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  167:           blk.18.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  168:             blk.18.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  169:           blk.18.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  170:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  171:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  172:             blk.19.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  173:             blk.19.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  174:             blk.19.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  175:        blk.19.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  176:           blk.19.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  177:             blk.19.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  178:           blk.19.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  179:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  180:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  181:             blk.20.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  182:             blk.20.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  183:             blk.20.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  184:        blk.20.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  185:           blk.20.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  186:             blk.20.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  187:           blk.20.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  188:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  189:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  190:             blk.21.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  191:             blk.21.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  192:             blk.21.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  193:        blk.21.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  194:           blk.21.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  195:             blk.21.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  196:           blk.21.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  197:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  198:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  199:             blk.22.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  200:             blk.22.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  201:             blk.22.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  202:        blk.22.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  203:           blk.22.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  204:             blk.22.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  205:           blk.22.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  206:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  207:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  208:             blk.23.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  209:             blk.23.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  210:             blk.23.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  211:        blk.23.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  212:           blk.23.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  213:             blk.23.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  214:           blk.23.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  215:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  216:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  217:             blk.24.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  218:             blk.24.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  219:             blk.24.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  220:        blk.24.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  221:           blk.24.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  222:             blk.24.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  223:           blk.24.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  224:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  225:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  226:             blk.25.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  227:             blk.25.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  228:             blk.25.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  229:        blk.25.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  230:           blk.25.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  231:             blk.25.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  232:           blk.25.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  233:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  234:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  235:             blk.26.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  236:             blk.26.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  237:             blk.26.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  238:        blk.26.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  239:           blk.26.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  240:             blk.26.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  241:           blk.26.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  242:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  243:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  244:             blk.27.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  245:             blk.27.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  246:             blk.27.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  247:        blk.27.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  248:           blk.27.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  249:             blk.27.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  250:           blk.27.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  251:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  252:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  253:             blk.28.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  254:             blk.28.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  255:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  256:        blk.28.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  257:           blk.28.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  258:             blk.28.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  259:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  260:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  261:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  262:             blk.29.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  263:             blk.29.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  264:             blk.29.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  265:        blk.29.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  266:           blk.29.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  267:             blk.29.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  268:           blk.29.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  269:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  270:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  271:             blk.30.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  272:             blk.30.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  273:             blk.30.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  274:        blk.30.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  275:           blk.30.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  276:             blk.30.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  277:           blk.30.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  278:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  279:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  280:             blk.31.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  281:             blk.31.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  282:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  283:        blk.31.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  284:           blk.31.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  285:             blk.31.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  286:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  287:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  288:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  289:               output_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  290:                    output.weight q6_K     [  4096, 32000,     1,     1 ]\n",
            "llama_model_loader: - kv   0:                       general.architecture str     \n",
            "llama_model_loader: - kv   1:                               general.name str     \n",
            "llama_model_loader: - kv   2:                       llama.context_length u32     \n",
            "llama_model_loader: - kv   3:                     llama.embedding_length u32     \n",
            "llama_model_loader: - kv   4:                          llama.block_count u32     \n",
            "llama_model_loader: - kv   5:                  llama.feed_forward_length u32     \n",
            "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32     \n",
            "llama_model_loader: - kv   7:                 llama.attention.head_count u32     \n",
            "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32     \n",
            "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32     \n",
            "llama_model_loader: - kv  10:                          general.file_type u32     \n",
            "llama_model_loader: - kv  11:                       tokenizer.ggml.model str     \n",
            "llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr     \n",
            "llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr     \n",
            "llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr     \n",
            "llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32     \n",
            "llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32     \n",
            "llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32     \n",
            "llama_model_loader: - kv  18:               general.quantization_version u32     \n",
            "llama_model_loader: - type  f32:   65 tensors\n",
            "llama_model_loader: - type q5_K:  193 tensors\n",
            "llama_model_loader: - type q6_K:   33 tensors\n",
            "llm_load_print_meta: format         = GGUF V2 (latest)\n",
            "llm_load_print_meta: arch           = llama\n",
            "llm_load_print_meta: vocab type     = SPM\n",
            "llm_load_print_meta: n_vocab        = 32000\n",
            "llm_load_print_meta: n_merges       = 0\n",
            "llm_load_print_meta: n_ctx_train    = 4096\n",
            "llm_load_print_meta: n_ctx          = 2048\n",
            "llm_load_print_meta: n_embd         = 4096\n",
            "llm_load_print_meta: n_head         = 32\n",
            "llm_load_print_meta: n_head_kv      = 32\n",
            "llm_load_print_meta: n_layer        = 32\n",
            "llm_load_print_meta: n_rot          = 128\n",
            "llm_load_print_meta: n_gqa          = 1\n",
            "llm_load_print_meta: f_norm_eps     = 1.0e-05\n",
            "llm_load_print_meta: f_norm_rms_eps = 1.0e-05\n",
            "llm_load_print_meta: n_ff           = 11008\n",
            "llm_load_print_meta: freq_base      = 10000.0\n",
            "llm_load_print_meta: freq_scale     = 1\n",
            "llm_load_print_meta: model type     = 7B\n",
            "llm_load_print_meta: model ftype    = mostly Q5_K - Medium\n",
            "llm_load_print_meta: model size     = 6.74 B\n",
            "llm_load_print_meta: general.name   = LLaMA v2\n",
            "llm_load_print_meta: BOS token = 1 '<s>'\n",
            "llm_load_print_meta: EOS token = 2 '</s>'\n",
            "llm_load_print_meta: UNK token = 0 '<unk>'\n",
            "llm_load_print_meta: LF token  = 13 '<0x0A>'\n",
            "llm_load_tensors: ggml ctx size =    0.09 MB\n",
            "llm_load_tensors: using CUDA for GPU acceleration\n",
            "llm_load_tensors: mem required  =   86.03 MB (+ 1024.00 MB per state)\n",
            "llm_load_tensors: offloading 32 repeating layers to GPU\n",
            "llm_load_tensors: offloading non-repeating layers to GPU\n",
            "llm_load_tensors: offloading v cache to GPU\n",
            "llm_load_tensors: offloading k cache to GPU\n",
            "llm_load_tensors: offloaded 35/35 layers to GPU\n",
            "llm_load_tensors: VRAM used: 5499 MB\n",
            "..................................................................................................\n",
            "llama_new_context_with_model: kv self size  = 1024.00 MB\n",
            "llama_new_context_with_model: compute buffer total size =  153.41 MB\n",
            "llama_new_context_with_model: VRAM scratch buffer: 152.00 MB\n",
            "AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | \n",
            "2023-09-21 07:21:02 INFO:\u001b[32mLoaded the model in 33.05 seconds.\n",
            "\u001b[0m\n",
            "2023-09-21 07:21:02 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://5c6d11ff2e59c29355.gradio.live\n",
            "\n",
            "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    11.84 ms /    20 runs   (    0.59 ms per token,  1689.76 tokens per second)\n",
            "llama_print_timings: prompt eval time =   553.88 ms /    36 tokens (   15.39 ms per token,    65.00 tokens per second)\n",
            "llama_print_timings:        eval time =   486.61 ms /    19 runs   (   25.61 ms per token,    39.05 tokens per second)\n",
            "llama_print_timings:       total time =  1104.08 ms\n",
            "Output generated in 1.86 seconds (10.24 tokens/s, 19 tokens, context 36, seed 1683207520)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    37.61 ms /    65 runs   (    0.58 ms per token,  1728.49 tokens per second)\n",
            "llama_print_timings: prompt eval time =   698.66 ms /    80 tokens (    8.73 ms per token,   114.51 tokens per second)\n",
            "llama_print_timings:        eval time =  1694.88 ms /    64 runs   (   26.48 ms per token,    37.76 tokens per second)\n",
            "llama_print_timings:       total time =  2594.40 ms\n",
            "Output generated in 3.33 seconds (19.23 tokens/s, 64 tokens, context 86, seed 649004890)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =   195.62 ms /   264 runs   (    0.74 ms per token,  1349.53 tokens per second)\n",
            "llama_print_timings: prompt eval time =   519.33 ms /    59 tokens (    8.80 ms per token,   113.61 tokens per second)\n",
            "llama_print_timings:        eval time =  7093.40 ms /   263 runs   (   26.97 ms per token,    37.08 tokens per second)\n",
            "llama_print_timings:       total time =  9086.51 ms\n",
            "Output generated in 9.84 seconds (26.73 tokens/s, 263 tokens, context 65, seed 586263663)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    13.17 ms /    23 runs   (    0.57 ms per token,  1746.92 tokens per second)\n",
            "llama_print_timings: prompt eval time =   539.16 ms /    60 tokens (    8.99 ms per token,   111.28 tokens per second)\n",
            "llama_print_timings:        eval time =   587.72 ms /    22 runs   (   26.71 ms per token,    37.43 tokens per second)\n",
            "llama_print_timings:       total time =  1198.27 ms\n",
            "Output generated in 1.95 seconds (11.29 tokens/s, 22 tokens, context 66, seed 730287844)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    22.53 ms /    20 runs   (    1.13 ms per token,   887.74 tokens per second)\n",
            "llama_print_timings: prompt eval time =   531.34 ms /    54 tokens (    9.84 ms per token,   101.63 tokens per second)\n",
            "llama_print_timings:        eval time =   496.17 ms /    19 runs   (   26.11 ms per token,    38.29 tokens per second)\n",
            "llama_print_timings:       total time =  1222.41 ms\n",
            "Output generated in 2.24 seconds (8.47 tokens/s, 19 tokens, context 60, seed 953232953)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =     3.05 ms /     3 runs   (    1.02 ms per token,   984.57 tokens per second)\n",
            "llama_print_timings: prompt eval time =   515.95 ms /    41 tokens (   12.58 ms per token,    79.46 tokens per second)\n",
            "llama_print_timings:        eval time =    52.11 ms /     2 runs   (   26.05 ms per token,    38.38 tokens per second)\n",
            "llama_print_timings:       total time =   591.71 ms\n",
            "Output generated in 1.58 seconds (1.26 tokens/s, 2 tokens, context 47, seed 1136301343)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =     8.49 ms /     9 runs   (    0.94 ms per token,  1060.07 tokens per second)\n",
            "llama_print_timings: prompt eval time =   516.75 ms /    48 tokens (   10.77 ms per token,    92.89 tokens per second)\n",
            "llama_print_timings:        eval time =   203.91 ms /     8 runs   (   25.49 ms per token,    39.23 tokens per second)\n",
            "llama_print_timings:       total time =   796.56 ms\n",
            "Output generated in 1.80 seconds (4.45 tokens/s, 8 tokens, context 54, seed 1590323651)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =     2.48 ms /     2 runs   (    1.24 ms per token,   808.08 tokens per second)\n",
            "llama_print_timings: prompt eval time =   398.34 ms /    28 tokens (   14.23 ms per token,    70.29 tokens per second)\n",
            "llama_print_timings:        eval time =    25.61 ms /     1 runs   (   25.61 ms per token,    39.05 tokens per second)\n",
            "llama_print_timings:       total time =   435.60 ms\n",
            "Output generated in 1.45 seconds (0.69 tokens/s, 1 tokens, context 34, seed 281154166)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    17.78 ms /    31 runs   (    0.57 ms per token,  1743.92 tokens per second)\n",
            "llama_print_timings: prompt eval time =   396.55 ms /    17 tokens (   23.33 ms per token,    42.87 tokens per second)\n",
            "llama_print_timings:        eval time =   824.55 ms /    30 runs   (   27.48 ms per token,    36.38 tokens per second)\n",
            "llama_print_timings:       total time =  1324.36 ms\n",
            "Output generated in 2.09 seconds (14.34 tokens/s, 30 tokens, context 23, seed 1696572958)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    11.46 ms /    11 runs   (    1.04 ms per token,   960.03 tokens per second)\n",
            "llama_print_timings: prompt eval time =   542.17 ms /    55 tokens (    9.86 ms per token,   101.44 tokens per second)\n",
            "llama_print_timings:        eval time =   258.08 ms /    10 runs   (   25.81 ms per token,    38.75 tokens per second)\n",
            "llama_print_timings:       total time =   892.90 ms\n",
            "Output generated in 1.83 seconds (5.48 tokens/s, 10 tokens, context 61, seed 1035849421)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    10.70 ms /    10 runs   (    1.07 ms per token,   934.93 tokens per second)\n",
            "llama_print_timings: prompt eval time =   386.61 ms /    25 tokens (   15.46 ms per token,    64.66 tokens per second)\n",
            "llama_print_timings:        eval time =   231.38 ms /     9 runs   (   25.71 ms per token,    38.90 tokens per second)\n",
            "llama_print_timings:       total time =   698.64 ms\n",
            "Output generated in 1.70 seconds (5.30 tokens/s, 9 tokens, context 31, seed 1114337361)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    45.73 ms /    72 runs   (    0.64 ms per token,  1574.32 tokens per second)\n",
            "llama_print_timings: prompt eval time =  1026.67 ms /   184 tokens (    5.58 ms per token,   179.22 tokens per second)\n",
            "llama_print_timings:        eval time =  2084.34 ms /    71 runs   (   29.36 ms per token,    34.06 tokens per second)\n",
            "llama_print_timings:       total time =  3381.09 ms\n",
            "Output generated in 4.32 seconds (16.43 tokens/s, 71 tokens, context 190, seed 531246917)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    16.93 ms /    30 runs   (    0.56 ms per token,  1771.90 tokens per second)\n",
            "llama_print_timings: prompt eval time =  1517.89 ms /   263 tokens (    5.77 ms per token,   173.27 tokens per second)\n",
            "llama_print_timings:        eval time =   845.40 ms /    29 runs   (   29.15 ms per token,    34.30 tokens per second)\n",
            "llama_print_timings:       total time =  2455.37 ms\n",
            "Output generated in 3.20 seconds (9.06 tokens/s, 29 tokens, context 318, seed 940144823)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    31.62 ms /    32 runs   (    0.99 ms per token,  1011.86 tokens per second)\n",
            "llama_print_timings: prompt eval time =   391.32 ms /    16 tokens (   24.46 ms per token,    40.89 tokens per second)\n",
            "llama_print_timings:        eval time =   802.93 ms /    31 runs   (   25.90 ms per token,    38.61 tokens per second)\n",
            "llama_print_timings:       total time =  1453.16 ms\n",
            "Output generated in 2.48 seconds (12.51 tokens/s, 31 tokens, context 22, seed 1900852271)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =    46.27 ms /    38 runs   (    1.22 ms per token,   821.28 tokens per second)\n",
            "llama_print_timings: prompt eval time =   722.37 ms /    93 tokens (    7.77 ms per token,   128.74 tokens per second)\n",
            "llama_print_timings:        eval time =   974.19 ms /    37 runs   (   26.33 ms per token,    37.98 tokens per second)\n",
            "llama_print_timings:       total time =  2072.42 ms\n",
            "Output generated in 3.14 seconds (11.78 tokens/s, 37 tokens, context 99, seed 1234762111)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =   553.94 ms\n",
            "llama_print_timings:      sample time =   126.19 ms /   181 runs   (    0.70 ms per token,  1434.33 tokens per second)\n",
            "llama_print_timings: prompt eval time =  1015.03 ms /   175 tokens (    5.80 ms per token,   172.41 tokens per second)\n",
            "llama_print_timings:        eval time =  5155.95 ms /   180 runs   (   28.64 ms per token,    34.91 tokens per second)\n",
            "llama_print_timings:       total time =  7176.93 ms\n",
            "Output generated in 8.20 seconds (21.96 tokens/s, 180 tokens, context 181, seed 1667972990)\n"
          ]
        }
      ],
      "source": [
        "%cd /content\n",
        "!apt-get -y install -qq aria2\n",
        "\n",
        "!git clone -b V20230828 https://github.com/Troyanovsky/text-generation-webui\n",
        "%cd /content/text-generation-webui\n",
        "!pip install -r requirements.txt\n",
        "!pip install -U gradio==3.33.1\n",
        "\n",
        "!pip uninstall -y llama-cpp-python\n",
        "!CMAKE_ARGS=\"-DLLAMA_CUDA=on\" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir\n",
        "\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/TheBloke/Kuchiki-1.1-L2-7B-GGUF/resolve/main/kuchiki-1.1-l2-7b.Q5_K_M.gguf -d /content/text-generation-webui/models/ -o kuchiki-1.1-l2-7b.Q5_K_M.gguf\n",
        "\n",
        "%cd /content/text-generation-webui\n",
        "!python server.py --share --n-gpu-layers 1000000000 --model kuchiki-1.1-l2-7b.Q5_K_M.gguf"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyP5dyfZSTuAdmFV0tPCfDaC",
      "include_colab_link": true
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}