LLaMA_Pro_8B_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/LLaMA_Pro_8B_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": [
        "## LLaMA-Pro-8B-GGUF WebUI\n",
        "\n",
        "1. Run the following cell, takes ~5 min\n",
        "(You may need to confirm to proceed by typing \"Y\")\n",
        "2. Pick the version you need from one of the last two cells and only run that cell.\n",
        "3. Click the gradio link at the bottom\n",
        "4. In Chat settings - Instruction Template: Unknown\n",
        "\n",
        "```\n",
        "<|user|>\n",
        "Your message here!\n",
        "<|assistant|>\n",
        "\n",
        "```\n",
        "(For best results, format all inputs in this manner. Make sure to include a newline after <|assistant|>, this can affect generation quality quite a bit.)\n",
        "https://huggingface.co/TencentARC/LLaMA-Pro-8B-Instruct/discussions/3"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "D-MiHp_bveP6",
        "outputId": "458132c2-908e-4057-b721-98c896bba07b"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content\n",
            "Selecting previously unselected package libc-ares2:amd64.\n",
            "(Reading database ... 121654 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 (2.35-0ubuntu3.4) ...\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",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc_proxy.so.2 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/libtbbbind_2_0.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_5.so.3 is not a symbolic link\n",
            "\n",
            "Cloning into 'text-generation-webui'...\n",
            "remote: Enumerating objects: 15569, done.\u001b[K\n",
            "remote: Total 15569 (delta 0), reused 0 (delta 0), pack-reused 15569\u001b[K\n",
            "Receiving objects: 100% (15569/15569), 26.02 MiB | 20.40 MiB/s, done.\n",
            "Resolving deltas: 100% (10847/10847), done.\n",
            "Note: switching to '11288d11d42f0be9a9d079c03d34c573a5cc696d'.\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 exllamav2: markers 'platform_system != \"Darwin\" and platform_machine != \"x86_64\"' don't match your environment\n",
            "Ignoring bitsandbytes: markers 'platform_system == \"Windows\"' don't match your environment\n",
            "Ignoring llama-cpp-python: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting llama-cpp-python==0.2.24+cpuavx2 (from -r requirements.txt (line 31))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.24+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl (2.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring llama-cpp-python: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring llama-cpp-python: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring llama-cpp-python: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring llama-cpp-python: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring llama-cpp-python: markers 'platform_system == \"Windows\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring llama-cpp-python: markers 'platform_system == \"Windows\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda: markers 'platform_system == \"Windows\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda: markers 'platform_system == \"Windows\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting llama-cpp-python-cuda==0.2.24+cu121 (from -r requirements.txt (line 45))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.24+cu121-cp310-cp310-manylinux_2_31_x86_64.whl (28.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m28.1/28.1 MB\u001b[0m \u001b[31m36.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring llama-cpp-python-cuda: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Windows\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Windows\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting llama-cpp-python-cuda-tensorcores==0.2.24+cu121 (from -r requirements.txt (line 55))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.24+cu121-cp310-cp310-manylinux_2_31_x86_64.whl (15.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.4/15.4 MB\u001b[0m \u001b[31m87.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring auto-gptq: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring auto-gptq: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring auto-gptq: markers 'platform_system == \"Windows\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring auto-gptq: markers 'platform_system == \"Windows\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring auto-gptq: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting auto-gptq==0.6.0+cu121 (from -r requirements.txt (line 65))\n",
            "  Downloading https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl (4.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.8/4.8 MB\u001b[0m \u001b[31m106.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring auto-gptq: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring auto-gptq: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring exllama: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring exllama: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring exllama: markers 'platform_system == \"Windows\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring exllama: markers 'platform_system == \"Windows\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring exllama: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting exllama==0.0.18+cu121 (from -r requirements.txt (line 73))\n",
            "  Downloading https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+cu121-cp310-cp310-linux_x86_64.whl (434 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m434.6/434.6 kB\u001b[0m \u001b[31m47.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring exllama: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring exllama: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring exllamav2: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring exllamav2: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring exllamav2: markers 'platform_system == \"Windows\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring exllamav2: markers 'platform_system == \"Windows\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring exllamav2: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting exllamav2==0.0.11+cu121 (from -r requirements.txt (line 81))\n",
            "  Downloading https://github.com/turboderp/exllamav2/releases/download/v0.0.11/exllamav2-0.0.11+cu121-cp310-cp310-linux_x86_64.whl (37.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m37.0/37.0 MB\u001b[0m \u001b[31m12.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring exllamav2: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring exllamav2: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring flash-attn: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring flash-attn: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring flash-attn: markers 'platform_system == \"Windows\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring flash-attn: markers 'platform_system == \"Windows\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring flash-attn: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting flash-attn==2.3.4+cu122torch2.1cxx11abiFALSE (from -r requirements.txt (line 89))\n",
            "  Downloading https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.4/flash_attn-2.3.4+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl (57.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.4/57.4 MB\u001b[0m \u001b[31m10.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring flash-attn: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring flash-attn: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring gptq-for-llama: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring gptq-for-llama: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring gptq-for-llama: markers 'platform_system == \"Windows\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring gptq-for-llama: markers 'platform_system == \"Windows\" and python_version == \"3.8\"' don't match your environment\n",
            "Ignoring gptq-for-llama: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting gptq-for-llama==0.1.1+cu121 (from -r requirements.txt (line 97))\n",
            "  Downloading https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl (739 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m739.5/739.5 kB\u001b[0m \u001b[31m72.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring gptq-for-llama: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.9\"' don't match your environment\n",
            "Ignoring gptq-for-llama: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.8\"' don't match your environment\n",
            "Collecting ctransformers==0.2.27+cu121 (from -r requirements.txt (line 100))\n",
            "  Downloading https://github.com/jllllll/ctransformers-cuBLAS-wheels/releases/download/AVX2/ctransformers-0.2.27+cu121-py3-none-any.whl (15.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.5/15.5 MB\u001b[0m \u001b[31m64.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting accelerate==0.25.* (from -r requirements.txt (line 1))\n",
            "  Downloading accelerate-0.25.0-py3-none-any.whl (265 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m265.7/265.7 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting colorama (from -r requirements.txt (line 2))\n",
            "  Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
            "Collecting datasets (from -r requirements.txt (line 3))\n",
            "  Downloading datasets-2.16.1-py3-none-any.whl (507 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m507.1/507.1 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting einops (from -r requirements.txt (line 4))\n",
            "  Downloading einops-0.7.0-py3-none-any.whl (44 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m6.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting gradio==3.50.* (from -r requirements.txt (line 6))\n",
            "  Downloading gradio-3.50.2-py3-none-any.whl (20.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m20.3/20.3 MB\u001b[0m \u001b[31m51.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting hqq==0.1.1.post1 (from -r requirements.txt (line 7))\n",
            "  Downloading hqq-0.1.1.post1.tar.gz (22 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: markdown in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 8)) (3.5.1)\n",
            "Collecting numpy==1.24.* (from -r requirements.txt (line 9))\n",
            "  Downloading numpy-1.24.4-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[31m89.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting optimum==1.16.* (from -r requirements.txt (line 10))\n",
            "  Downloading optimum-1.16.1-py3-none-any.whl (403 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m403.3/403.3 kB\u001b[0m \u001b[31m48.4 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 11)) (1.5.3)\n",
            "Collecting peft==0.7.* (from -r requirements.txt (line 12))\n",
            "  Downloading peft-0.7.1-py3-none-any.whl (168 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m168.3/168.3 kB\u001b[0m \u001b[31m24.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting Pillow>=9.5.0 (from -r requirements.txt (line 13))\n",
            "  Downloading pillow-10.2.0-cp310-cp310-manylinux_2_28_x86_64.whl (4.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.5/4.5 MB\u001b[0m \u001b[31m22.5 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 14)) (6.0.1)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 15)) (2.31.0)\n",
            "Requirement already satisfied: rich in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 16)) (13.7.0)\n",
            "Requirement already satisfied: safetensors==0.4.1 in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 17)) (0.4.1)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 18)) (1.11.4)\n",
            "Collecting sentencepiece (from -r requirements.txt (line 19))\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[31m87.8 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 20)) (2.15.1)\n",
            "Collecting transformers==4.36.* (from -r requirements.txt (line 21))\n",
            "  Downloading transformers-4.36.2-py3-none-any.whl (8.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.2/8.2 MB\u001b[0m \u001b[31m109.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 22)) (4.66.1)\n",
            "Collecting wandb (from -r requirements.txt (line 23))\n",
            "  Downloading wandb-0.16.2-py3-none-any.whl (2.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m97.7 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[31m10.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting autoawq==0.1.7 (from -r requirements.txt (line 101))\n",
            "  Downloading autoawq-0.1.7-cp310-cp310-manylinux2014_x86_64.whl (20.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m20.5/20.5 MB\u001b[0m \u001b[31m85.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.25.*->-r requirements.txt (line 1)) (23.2)\n",
            "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate==0.25.*->-r requirements.txt (line 1)) (5.9.5)\n",
            "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.25.*->-r requirements.txt (line 1)) (2.1.0+cu121)\n",
            "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate==0.25.*->-r requirements.txt (line 1)) (0.20.2)\n",
            "Collecting aiofiles<24.0,>=22.0 (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
            "Requirement already satisfied: altair<6.0,>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.*->-r requirements.txt (line 6)) (4.2.2)\n",
            "Collecting fastapi (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading fastapi-0.109.0-py3-none-any.whl (92 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.0/92.0 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting ffmpy (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading ffmpy-0.3.1.tar.gz (5.5 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting gradio-client==0.6.1 (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading gradio_client-0.6.1-py3-none-any.whl (299 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m299.2/299.2 kB\u001b[0m \u001b[31m39.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting httpx (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading httpx-0.26.0-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.*->-r requirements.txt (line 6)) (6.1.1)\n",
            "Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.*->-r requirements.txt (line 6)) (3.1.2)\n",
            "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.*->-r requirements.txt (line 6)) (2.1.3)\n",
            "Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.*->-r requirements.txt (line 6)) (3.7.1)\n",
            "Collecting orjson~=3.0 (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading orjson-3.9.10-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[31m21.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,<3.0.0,>=1.7.4 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.*->-r requirements.txt (line 6)) (1.10.13)\n",
            "Collecting pydub (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
            "Collecting python-multipart (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading python_multipart-0.0.6-py3-none-any.whl (45 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.7/45.7 kB\u001b[0m \u001b[31m7.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting semantic-version~=2.0 (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
            "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.*->-r requirements.txt (line 6)) (4.5.0)\n",
            "Collecting uvicorn>=0.14.0 (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading uvicorn-0.25.0-py3-none-any.whl (60 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.3/60.3 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting websockets<12.0,>=10.0 (from gradio==3.50.*->-r requirements.txt (line 6))\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[31m19.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting timm (from hqq==0.1.1.post1->-r requirements.txt (line 7))\n",
            "  Downloading timm-0.9.12-py3-none-any.whl (2.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m98.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: termcolor in /usr/local/lib/python3.10/dist-packages (from hqq==0.1.1.post1->-r requirements.txt (line 7)) (2.4.0)\n",
            "Collecting coloredlogs (from optimum==1.16.*->-r requirements.txt (line 10))\n",
            "  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from optimum==1.16.*->-r requirements.txt (line 10)) (1.12)\n",
            "Requirement already satisfied: transformers[sentencepiece]>=4.26.0 in /usr/local/lib/python3.10/dist-packages (from optimum==1.16.*->-r requirements.txt (line 10)) (4.35.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.*->-r requirements.txt (line 21)) (3.13.1)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.*->-r requirements.txt (line 21)) (2023.6.3)\n",
            "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.*->-r requirements.txt (line 21)) (0.15.0)\n",
            "Collecting lm-eval (from autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading lm_eval-0.4.0.tar.gz (457 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m457.1/457.1 kB\u001b[0m \u001b[31m52.4 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",
            "Collecting texttable (from autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading texttable-1.7.0-py2.py3-none-any.whl (10 kB)\n",
            "Requirement already satisfied: toml in /usr/local/lib/python3.10/dist-packages (from autoawq==0.1.7->-r requirements.txt (line 101)) (0.10.2)\n",
            "Collecting attributedict (from autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading attributedict-0.3.0-py3-none-any.whl (14 kB)\n",
            "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from autoawq==0.1.7->-r requirements.txt (line 101)) (3.20.3)\n",
            "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (from autoawq==0.1.7->-r requirements.txt (line 101)) (0.16.0+cu121)\n",
            "Requirement already satisfied: tabulate in /usr/local/lib/python3.10/dist-packages (from autoawq==0.1.7->-r requirements.txt (line 101)) (0.9.0)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.6.1->gradio==3.50.*->-r requirements.txt (line 6)) (2023.6.0)\n",
            "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets->-r requirements.txt (line 3)) (10.0.1)\n",
            "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets->-r requirements.txt (line 3)) (0.6)\n",
            "Collecting dill<0.3.8,>=0.3.0 (from datasets->-r requirements.txt (line 3))\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[31m19.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets->-r requirements.txt (line 3)) (3.4.1)\n",
            "Collecting multiprocess (from datasets->-r requirements.txt (line 3))\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[31m22.0 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 datasets->-r requirements.txt (line 3)) (3.9.1)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 11)) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 11)) (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 15)) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 15)) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 15)) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 15)) (2023.11.17)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich->-r requirements.txt (line 16)) (3.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich->-r requirements.txt (line 16)) (2.16.1)\n",
            "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 20)) (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 20)) (1.60.0)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 20)) (2.17.3)\n",
            "Requirement already satisfied: google-auth-oauthlib<2,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 20)) (1.2.0)\n",
            "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 20)) (67.7.2)\n",
            "Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 20)) (1.16.0)\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 20)) (0.7.2)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 20)) (3.0.1)\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-3.1.41-py3-none-any.whl (196 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.4/196.4 kB\u001b[0m \u001b[31m28.8 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-1.39.2-py2.py3-none-any.whl (254 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m254.1/254.1 kB\u001b[0m \u001b[31m36.0 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 setproctitle (from wandb->-r requirements.txt (line 23))\n",
            "  Downloading setproctitle-1.3.3-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",
            "Requirement already satisfied: diskcache>=5.6.1 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python==0.2.24+cpuavx2->-r requirements.txt (line 31)) (5.6.3)\n",
            "Collecting rouge (from auto-gptq==0.6.0+cu121->-r requirements.txt (line 65))\n",
            "  Downloading rouge-1.0.1-py3-none-any.whl (13 kB)\n",
            "Collecting gekko (from auto-gptq==0.6.0+cu121->-r requirements.txt (line 65))\n",
            "  Downloading gekko-1.0.6-py3-none-any.whl (12.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.2/12.2 MB\u001b[0m \u001b[31m110.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting ninja (from exllamav2==0.0.11+cu121->-r requirements.txt (line 81))\n",
            "  Downloading ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl (307 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m307.2/307.2 kB\u001b[0m \u001b[31m40.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting fastparquet (from exllamav2==0.0.11+cu121->-r requirements.txt (line 81))\n",
            "  Downloading fastparquet-2023.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.7 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m100.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: py-cpuinfo<10.0.0,>=9.0.0 in /usr/local/lib/python3.10/dist-packages (from ctransformers==0.2.27+cu121->-r requirements.txt (line 100)) (9.0.0)\n",
            "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.*->-r requirements.txt (line 6)) (0.4)\n",
            "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.*->-r requirements.txt (line 6)) (4.19.2)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.*->-r requirements.txt (line 6)) (0.12.0)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 3)) (23.2.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 3)) (6.0.4)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 3)) (1.9.4)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 3)) (1.4.1)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 3)) (1.3.1)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 3)) (4.0.3)\n",
            "Collecting gitdb<5,>=4.0.1 (from GitPython!=3.1.29,>=1.0.0->wandb->-r requirements.txt (line 23))\n",
            "  Downloading gitdb-4.0.11-py3-none-any.whl (62 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m10.0 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 20)) (5.3.2)\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 20)) (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 20)) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<2,>=0.5->tensorboard->-r requirements.txt (line 20)) (1.3.1)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich->-r requirements.txt (line 16)) (0.1.2)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.*->-r requirements.txt (line 6)) (1.2.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.*->-r requirements.txt (line 6)) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.*->-r requirements.txt (line 6)) (4.47.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.*->-r requirements.txt (line 6)) (1.4.5)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.*->-r requirements.txt (line 6)) (3.1.1)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.25.*->-r requirements.txt (line 1)) (3.2.1)\n",
            "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.25.*->-r requirements.txt (line 1)) (2.1.0)\n",
            "INFO: pip is looking at multiple versions of transformers[sentencepiece] to determine which version is compatible with other requirements. This could take a while.\n",
            "Collecting h11>=0.8 (from uvicorn>=0.14.0->gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting rootpath>=0.1.0 (from attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading rootpath-0.1.1-py3-none-any.whl (15 kB)\n",
            "Collecting inspecta>=0.1.0 (from attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading inspecta-0.1.3-py3-none-any.whl (9.2 kB)\n",
            "Collecting colour-runner>=0.0.5 (from attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading colour_runner-0.1.1-py2.py3-none-any.whl (3.7 kB)\n",
            "Collecting deepdiff>=3.3.0 (from attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading deepdiff-6.7.1-py3-none-any.whl (76 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.6/76.6 kB\u001b[0m \u001b[31m13.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting tox>=3.0.0 (from attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading tox-4.12.0-py3-none-any.whl (154 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.4/154.4 kB\u001b[0m \u001b[31m24.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting coverage>=4.5.2 (from attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading coverage-7.4.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (233 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m233.2/233.2 kB\u001b[0m \u001b[31m28.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting codecov>=2.0.15 (from attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading codecov-2.1.13-py2.py3-none-any.whl (16 kB)\n",
            "Collecting humanfriendly>=9.1 (from coloredlogs->optimum==1.16.*->-r requirements.txt (line 10))\n",
            "  Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m14.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting starlette<0.36.0,>=0.35.0 (from fastapi->gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading starlette-0.35.1-py3-none-any.whl (71 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.1/71.1 kB\u001b[0m \u001b[31m11.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting typing-extensions~=4.0 (from gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading typing_extensions-4.9.0-py3-none-any.whl (32 kB)\n",
            "Collecting cramjam>=2.3 (from fastparquet->exllamav2==0.0.11+cu121->-r requirements.txt (line 81))\n",
            "  Downloading cramjam-2.8.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.9 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.9/1.9 MB\u001b[0m \u001b[31m68.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.50.*->-r requirements.txt (line 6)) (3.7.1)\n",
            "Collecting httpcore==1.* (from httpx->gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading httpcore-1.0.2-py3-none-any.whl (76 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m12.0 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==3.50.*->-r requirements.txt (line 6)) (1.3.0)\n",
            "Collecting evaluate (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading evaluate-0.4.1-py3-none-any.whl (84 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.1/84.1 kB\u001b[0m \u001b[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting jsonlines (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading jsonlines-4.0.0-py3-none-any.whl (8.7 kB)\n",
            "Requirement already satisfied: numexpr in /usr/local/lib/python3.10/dist-packages (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101)) (2.8.8)\n",
            "Collecting pybind11>=2.6.2 (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading pybind11-2.11.1-py3-none-any.whl (227 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.7/227.7 kB\u001b[0m \u001b[31m26.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pytablewriter (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading pytablewriter-1.2.0-py3-none-any.whl (111 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m111.1/111.1 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting rouge-score>=0.0.4 (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading rouge_score-0.1.2.tar.gz (17 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting sacrebleu>=1.5.0 (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading sacrebleu-2.4.0-py3-none-any.whl (106 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m106.3/106.3 kB\u001b[0m \u001b[31m17.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: scikit-learn>=0.24.1 in /usr/local/lib/python3.10/dist-packages (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101)) (1.2.2)\n",
            "Collecting sqlitedict (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading sqlitedict-2.1.0.tar.gz (21 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting tqdm-multiprocess (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading tqdm_multiprocess-0.0.11-py3-none-any.whl (9.8 kB)\n",
            "Collecting zstandard (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading zstandard-0.22.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m112.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->optimum==1.16.*->-r requirements.txt (line 10)) (1.3.0)\n",
            "Collecting blessings (from colour-runner>=0.0.5->attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading blessings-1.7-py3-none-any.whl (18 kB)\n",
            "Collecting ordered-set<4.2.0,>=4.0.2 (from deepdiff>=3.3.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading ordered_set-4.1.0-py3-none-any.whl (7.6 kB)\n",
            "Collecting responses<0.19 (from evaluate->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading responses-0.18.0-py3-none-any.whl (38 kB)\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<6.0,>=4.2.0->gradio==3.50.*->-r requirements.txt (line 6)) (2023.12.1)\n",
            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.*->-r requirements.txt (line 6)) (0.32.1)\n",
            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.*->-r requirements.txt (line 6)) (0.16.2)\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 20)) (0.5.1)\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<2,>=0.5->tensorboard->-r requirements.txt (line 20)) (3.2.2)\n",
            "Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from rouge-score>=0.0.4->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101)) (3.8.1)\n",
            "Collecting portalocker (from sacrebleu>=1.5.0->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading portalocker-2.8.2-py3-none-any.whl (17 kB)\n",
            "Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from sacrebleu>=1.5.0->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101)) (4.9.4)\n",
            "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.24.1->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101)) (1.3.2)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.24.1->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101)) (3.2.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx->gradio==3.50.*->-r requirements.txt (line 6)) (1.2.0)\n",
            "Requirement already satisfied: chardet>=5.2 in /usr/local/lib/python3.10/dist-packages (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 101)) (5.2.0)\n",
            "Requirement already satisfied: platformdirs>=4.1 in /usr/local/lib/python3.10/dist-packages (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 101)) (4.1.0)\n",
            "Requirement already satisfied: pluggy>=1.3 in /usr/local/lib/python3.10/dist-packages (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 101)) (1.3.0)\n",
            "Collecting pyproject-api>=1.6.1 (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading pyproject_api-1.6.1-py3-none-any.whl (12 kB)\n",
            "Requirement already satisfied: tomli>=2.0.1 in /usr/local/lib/python3.10/dist-packages (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 101)) (2.0.1)\n",
            "Collecting virtualenv>=20.25 (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading virtualenv-20.25.0-py3-none-any.whl (3.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.8/3.8 MB\u001b[0m \u001b[31m115.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting DataProperty<2,>=1.0.1 (from pytablewriter->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading DataProperty-1.0.1-py3-none-any.whl (27 kB)\n",
            "Collecting mbstrdecoder<2,>=1.0.0 (from pytablewriter->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading mbstrdecoder-1.1.3-py3-none-any.whl (7.8 kB)\n",
            "Collecting pathvalidate<4,>=2.3.0 (from pytablewriter->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading pathvalidate-3.2.0-py3-none-any.whl (23 kB)\n",
            "Collecting tabledata<2,>=1.3.1 (from pytablewriter->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading tabledata-1.3.3-py3-none-any.whl (11 kB)\n",
            "Collecting tcolorpy<1,>=0.0.5 (from pytablewriter->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading tcolorpy-0.1.4-py3-none-any.whl (7.9 kB)\n",
            "Collecting typepy[datetime]<2,>=1.3.2 (from pytablewriter->lm-eval->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading typepy-1.3.2-py3-none-any.whl (31 kB)\n",
            "Collecting distlib<1,>=0.3.7 (from virtualenv>=20.25->tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 101))\n",
            "  Downloading distlib-0.3.8-py2.py3-none-any.whl (468 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m468.9/468.9 kB\u001b[0m \u001b[31m55.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hBuilding wheels for collected packages: hqq, ffmpy, lm-eval, rouge-score, sqlitedict\n",
            "  Building wheel for hqq (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for hqq: filename=hqq-0.1.1.post1-py3-none-any.whl size=28828 sha256=a618f95b732a422a0ff1a1fd27431ed2b643196b8ed8993333f441bea4146d5b\n",
            "  Stored in directory: /root/.cache/pip/wheels/11/f2/ae/7bf67b9d73250d780b21357a818e06d24a7d9ea27b2bd9369d\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=467144b9cc328868ca93cf47d0f275062fa295d5f04ffa81cdbc1487af72c34c\n",
            "  Stored in directory: /root/.cache/pip/wheels/01/a6/d1/1c0828c304a4283b2c1639a09ad86f83d7c487ef34c6b4a1bf\n",
            "  Building wheel for lm-eval (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for lm-eval: filename=lm_eval-0.4.0-py3-none-any.whl size=994996 sha256=a0276ae2c548d10935d59281ddbd2b6036fcb105b24bbbee33f300aa1bc0fe00\n",
            "  Stored in directory: /root/.cache/pip/wheels/45/b5/b3/4d97da1bde0b79da99e75ec0eb69f838d1fe02f83ab7a01bb4\n",
            "  Building wheel for rouge-score (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for rouge-score: filename=rouge_score-0.1.2-py3-none-any.whl size=24933 sha256=d933dea8fa110e01c1841ca288ca66464f58fe8f71ca9095cfb5f197c8c6926e\n",
            "  Stored in directory: /root/.cache/pip/wheels/5f/dd/89/461065a73be61a532ff8599a28e9beef17985c9e9c31e541b4\n",
            "  Building wheel for sqlitedict (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for sqlitedict: filename=sqlitedict-2.1.0-py3-none-any.whl size=16863 sha256=bb5e06631723c4f95a645ce4c528c4f252e66a288240507d1462dce5c21c4819\n",
            "  Stored in directory: /root/.cache/pip/wheels/79/d6/e7/304e0e6cb2221022c26d8161f7c23cd4f259a9e41e8bbcfabd\n",
            "Successfully built hqq ffmpy lm-eval rouge-score sqlitedict\n",
            "Installing collected packages: texttable, sqlitedict, sentencepiece, pydub, ninja, gptq-for-llama, ffmpy, distlib, bitsandbytes, zstandard, websockets, virtualenv, typing-extensions, tcolorpy, smmap, setproctitle, sentry-sdk, semantic-version, rouge, python-multipart, pyproject-api, pybind11, portalocker, Pillow, pathvalidate, orjson, ordered-set, numpy, mbstrdecoder, jsonlines, humanfriendly, h11, einops, docker-pycreds, dill, cramjam, coverage, colorama, blessings, aiofiles, uvicorn, typepy, tqdm-multiprocess, tox, starlette, sacrebleu, rouge-score, responses, multiprocess, llama-cpp-python-cuda-tensorcores, llama-cpp-python-cuda, llama-cpp-python, httpcore, gitdb, gekko, deepdiff, colour-runner, coloredlogs, codecov, rootpath, httpx, GitPython, flash-attn, fastparquet, fastapi, exllama, ctransformers, accelerate, wandb, transformers, timm, inspecta, gradio-client, exllamav2, datasets, DataProperty, tabledata, peft, hqq, gradio, evaluate, attributedict, pytablewriter, optimum, auto-gptq, lm-eval, autoawq\n",
            "  Attempting uninstall: typing-extensions\n",
            "    Found existing installation: typing_extensions 4.5.0\n",
            "    Uninstalling typing_extensions-4.5.0:\n",
            "      Successfully uninstalled typing_extensions-4.5.0\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: transformers\n",
            "    Found existing installation: transformers 4.35.2\n",
            "    Uninstalling transformers-4.35.2:\n",
            "      Successfully uninstalled transformers-4.35.2\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",
            "lida 0.0.10 requires kaleido, which is not installed.\n",
            "imageio 2.31.6 requires pillow<10.1.0,>=8.3.2, but you have pillow 10.2.0 which is incompatible.\n",
            "tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed DataProperty-1.0.1 GitPython-3.1.41 Pillow-10.2.0 accelerate-0.25.0 aiofiles-23.2.1 attributedict-0.3.0 auto-gptq-0.6.0+cu121 autoawq-0.1.7 bitsandbytes-0.41.1 blessings-1.7 codecov-2.1.13 colorama-0.4.6 coloredlogs-15.0.1 colour-runner-0.1.1 coverage-7.4.0 cramjam-2.8.0 ctransformers-0.2.27+cu121 datasets-2.16.1 deepdiff-6.7.1 dill-0.3.7 distlib-0.3.8 docker-pycreds-0.4.0 einops-0.7.0 evaluate-0.4.1 exllama-0.0.18+cu121 exllamav2-0.0.11+cu121 fastapi-0.109.0 fastparquet-2023.10.1 ffmpy-0.3.1 flash-attn-2.3.4 gekko-1.0.6 gitdb-4.0.11 gptq-for-llama-0.1.1+cu121 gradio-3.50.2 gradio-client-0.6.1 h11-0.14.0 hqq-0.1.1.post1 httpcore-1.0.2 httpx-0.26.0 humanfriendly-10.0 inspecta-0.1.3 jsonlines-4.0.0 llama-cpp-python-0.2.24+cpuavx2 llama-cpp-python-cuda-0.2.24+cu121 llama-cpp-python-cuda-tensorcores-0.2.24+cu121 lm-eval-0.4.0 mbstrdecoder-1.1.3 multiprocess-0.70.15 ninja-1.11.1.1 numpy-1.24.4 optimum-1.16.1 ordered-set-4.1.0 orjson-3.9.10 pathvalidate-3.2.0 peft-0.7.1 portalocker-2.8.2 pybind11-2.11.1 pydub-0.25.1 pyproject-api-1.6.1 pytablewriter-1.2.0 python-multipart-0.0.6 responses-0.18.0 rootpath-0.1.1 rouge-1.0.1 rouge-score-0.1.2 sacrebleu-2.4.0 semantic-version-2.10.0 sentencepiece-0.1.99 sentry-sdk-1.39.2 setproctitle-1.3.3 smmap-5.0.1 sqlitedict-2.1.0 starlette-0.35.1 tabledata-1.3.3 tcolorpy-0.1.4 texttable-1.7.0 timm-0.9.12 tox-4.12.0 tqdm-multiprocess-0.0.11 transformers-4.36.2 typepy-1.3.2 typing-extensions-4.9.0 uvicorn-0.25.0 virtualenv-20.25.0 wandb-0.16.2 websockets-11.0.3 zstandard-0.22.0\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==3.50.2 in /usr/local/lib/python3.10/dist-packages (3.50.2)\n",
            "Requirement already satisfied: aiofiles<24.0,>=22.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (23.2.1)\n",
            "Requirement already satisfied: altair<6.0,>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (4.2.2)\n",
            "Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.109.0)\n",
            "Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.3.1)\n",
            "Requirement already satisfied: gradio-client==0.6.1 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.6.1)\n",
            "Requirement already satisfied: httpx in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.26.0)\n",
            "Requirement already satisfied: huggingface-hub>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.20.2)\n",
            "Requirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (6.1.1)\n",
            "Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (3.1.2)\n",
            "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (2.1.3)\n",
            "Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (3.7.1)\n",
            "Requirement already satisfied: numpy~=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (1.24.4)\n",
            "Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (3.9.10)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (23.2)\n",
            "Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (1.5.3)\n",
            "Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (10.2.0)\n",
            "Requirement already satisfied: pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,<3.0.0,>=1.7.4 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (1.10.13)\n",
            "Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.25.1)\n",
            "Requirement already satisfied: python-multipart in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.0.6)\n",
            "Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (6.0.1)\n",
            "Requirement already satisfied: requests~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (2.31.0)\n",
            "Requirement already satisfied: semantic-version~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (2.10.0)\n",
            "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (4.9.0)\n",
            "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.25.0)\n",
            "Requirement already satisfied: websockets<12.0,>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (11.0.3)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.6.1->gradio==3.50.2) (2023.6.0)\n",
            "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.2) (0.4)\n",
            "Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.2) (4.19.2)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==3.50.2) (0.12.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.0->gradio==3.50.2) (3.13.1)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.14.0->gradio==3.50.2) (4.66.1)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2) (1.2.0)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2) (4.47.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2) (1.4.5)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2) (3.1.1)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==3.50.2) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio==3.50.2) (2023.3.post1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio==3.50.2) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio==3.50.2) (3.6)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio==3.50.2) (2.0.7)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests~=2.0->gradio==3.50.2) (2023.11.17)\n",
            "Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio==3.50.2) (8.1.7)\n",
            "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio==3.50.2) (0.14.0)\n",
            "Requirement already satisfied: starlette<0.36.0,>=0.35.0 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio==3.50.2) (0.35.1)\n",
            "Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.50.2) (3.7.1)\n",
            "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.50.2) (1.0.2)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx->gradio==3.50.2) (1.3.0)\n",
            "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2) (23.2.0)\n",
            "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2) (2023.12.1)\n",
            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2) (0.32.1)\n",
            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2) (0.16.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio==3.50.2) (1.16.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx->gradio==3.50.2) (1.2.0)\n",
            "Found existing installation: llama_cpp_python 0.2.24+cpuavx2\n",
            "Uninstalling llama_cpp_python-0.2.24+cpuavx2:\n",
            "  Successfully uninstalled llama_cpp_python-0.2.24+cpuavx2\n",
            "Collecting llama-cpp-python\n",
            "  Downloading llama_cpp_python-0.2.29.tar.gz (9.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.5/9.5 MB\u001b[0m \u001b[31m26.4 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) (4.9.0)\n",
            "Requirement already satisfied: numpy>=1.20.0 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python) (1.24.4)\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-0.2.29-cp310-cp310-manylinux_2_35_x86_64.whl size=9289567 sha256=7688d80d0c79e9a583aa994f5086aaeb2145ee52acb9ca1d3fb6def4ec471f4d\n",
            "  Stored in directory: /tmp/pip-ephem-wheel-cache-880rdkum/wheels/aa/09/8d/df365429984babf5a986216d50a8c5d465c4772399e2902397\n",
            "Successfully built llama-cpp-python\n",
            "Installing collected packages: llama-cpp-python\n",
            "Successfully installed llama-cpp-python-0.2.29\n",
            "Found existing installation: flash-attn 2.3.4\n",
            "Uninstalling flash-attn-2.3.4:\n",
            "  Successfully uninstalled flash-attn-2.3.4\n",
            "Collecting flash-attn==2.3.4\n",
            "  Downloading flash_attn-2.3.4.tar.gz (2.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m15.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from flash-attn==2.3.4) (2.1.0+cu121)\n",
            "Requirement already satisfied: einops in /usr/local/lib/python3.10/dist-packages (from flash-attn==2.3.4) (0.7.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from flash-attn==2.3.4) (23.2)\n",
            "Requirement already satisfied: ninja in /usr/local/lib/python3.10/dist-packages (from flash-attn==2.3.4) (1.11.1.1)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.3.4) (3.13.1)\n",
            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.3.4) (4.9.0)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.3.4) (1.12)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.3.4) (3.2.1)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.3.4) (3.1.2)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.3.4) (2023.6.0)\n",
            "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.3.4) (2.1.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->flash-attn==2.3.4) (2.1.3)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->flash-attn==2.3.4) (1.3.0)\n",
            "Building wheels for collected packages: flash-attn\n",
            "  Building wheel for flash-attn (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for flash-attn: filename=flash_attn-2.3.4-cp310-cp310-linux_x86_64.whl size=57390576 sha256=a4f74d7c46a5b6c86d3f7539b07d11a76e7bfe8089cbc1de8ee79f0cf984bb13\n",
            "  Stored in directory: /root/.cache/pip/wheels/32/19/1b/bf8147431c43f8b8d2b2e5d66be1ebf586f2fca96d72203f53\n",
            "Successfully built flash-attn\n",
            "Installing collected packages: flash-attn\n",
            "Successfully installed flash-attn-2.3.4\n",
            "\u001b[0m\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "786121|\u001b[1;32mOK\u001b[0m  |   169MiB/s|/content/text-generation-webui/models//llama-pro-8b.Q5_K_M.gguf\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "/content/text-generation-webui\n",
            "\u001b[2;36m09:21:28-817032\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Starting Text generation web UI                                            \n",
            "\u001b[2;36m09:21:28-958364\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Loading llama-pro-8b.Q5_K_M.gguf                                           \n",
            "\u001b[2;36m09:21:29-164941\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m llama.cpp weights detected: models/llama-pro-8b.Q5_K_M.gguf                \n",
            "ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   yes\n",
            "ggml_init_cublas: CUDA_USE_TENSOR_CORES: no\n",
            "ggml_init_cublas: found 1 CUDA devices:\n",
            "  Device 0: Tesla T4, compute capability 7.5\n",
            "llama_model_loader: loaded meta data with 22 key-value pairs and 363 tensors from models/llama-pro-8b.Q5_K_M.gguf (version GGUF V3 (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_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor    2:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    3:            blk.0.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor    4:              blk.0.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor    5:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor    6:              blk.0.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    7:         blk.0.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    8:              blk.0.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor    9:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   10:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   11:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   12:            blk.1.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   13:              blk.1.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   14:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   15:              blk.1.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   16:         blk.1.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   17:              blk.1.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   18:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   19:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   20:           blk.10.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   21:           blk.10.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   22:             blk.10.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   23:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   24:             blk.10.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   25:        blk.10.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   26:             blk.10.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   27:             blk.10.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   28:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   29:           blk.11.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   30:           blk.11.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   31:             blk.11.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   32:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   33:             blk.11.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   34:        blk.11.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   35:             blk.11.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   36:             blk.11.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   37:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   38:           blk.12.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   39:           blk.12.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   40:             blk.12.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   41:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   42:             blk.12.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   43:        blk.12.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   44:             blk.12.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   45:             blk.12.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   46:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   47:           blk.13.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   48:           blk.13.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   49:             blk.13.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   50:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   51:             blk.13.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   52:        blk.13.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   53:             blk.13.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   54:             blk.13.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   55:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   56:           blk.14.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   57:           blk.14.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   58:             blk.14.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   59:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   60:             blk.14.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   61:        blk.14.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   62:             blk.14.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   63:             blk.14.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   64:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   65:           blk.15.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   66:           blk.15.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   67:             blk.15.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   68:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   69:             blk.15.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   70:        blk.15.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   71:             blk.15.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   72:             blk.15.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   73:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   74:           blk.16.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   75:           blk.16.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   76:             blk.16.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   77:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   78:             blk.16.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   79:        blk.16.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   80:             blk.16.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   81:             blk.16.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   82:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   83:           blk.17.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   84:           blk.17.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   85:             blk.17.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   86:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   87:             blk.17.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   88:        blk.17.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   89:             blk.17.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   90:             blk.17.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   91:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   92:           blk.18.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   93:           blk.18.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   94:             blk.18.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor   95:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   96:             blk.18.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   97:        blk.18.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   98:             blk.18.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor   99:             blk.18.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  100:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  101:           blk.19.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  102:           blk.19.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  103:             blk.19.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  104:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  105:             blk.19.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  106:        blk.19.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  107:             blk.19.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  108:             blk.19.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  109:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  110:            blk.2.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  111:            blk.2.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  112:              blk.2.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  113:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  114:              blk.2.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  115:         blk.2.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  116:              blk.2.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  117:              blk.2.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  118:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  119:           blk.20.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  120:           blk.20.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  121:             blk.20.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  122:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  123:             blk.20.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  124:        blk.20.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  125:             blk.20.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  126:             blk.20.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  127:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  128:           blk.21.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  129:           blk.21.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  130:             blk.21.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  131:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  132:             blk.21.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  133:        blk.21.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  134:             blk.21.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  135:             blk.21.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  136:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  137:           blk.22.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  138:           blk.22.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  139:             blk.22.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  140:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  141:             blk.22.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  142:        blk.22.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  143:             blk.22.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  144:             blk.22.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  145:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  146:           blk.23.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  147:           blk.23.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  148:             blk.23.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  149:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  150:             blk.23.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  151:        blk.23.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  152:             blk.23.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  153:             blk.23.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  154:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  155:            blk.3.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  156:            blk.3.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  157:              blk.3.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  158:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  159:              blk.3.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  160:         blk.3.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  161:              blk.3.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  162:              blk.3.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  163:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  164:            blk.4.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  165:            blk.4.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  166:              blk.4.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  167:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  168:              blk.4.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  169:         blk.4.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  170:              blk.4.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  171:              blk.4.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  172:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  173:            blk.5.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  174:            blk.5.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  175:              blk.5.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  176:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  177:              blk.5.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  178:         blk.5.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  179:              blk.5.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  180:              blk.5.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  181:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  182:            blk.6.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  183:            blk.6.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  184:              blk.6.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  185:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  186:              blk.6.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  187:         blk.6.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  188:              blk.6.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  189:              blk.6.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  190:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  191:            blk.7.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  192:            blk.7.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  193:              blk.7.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  194:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  195:              blk.7.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  196:         blk.7.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  197:              blk.7.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  198:              blk.7.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  199:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  200:            blk.8.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  201:            blk.8.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  202:              blk.8.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  203:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  204:              blk.8.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  205:         blk.8.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  206:              blk.8.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  207:              blk.8.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  208:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  209:            blk.9.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  210:            blk.9.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  211:              blk.9.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  212:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  213:              blk.9.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  214:         blk.9.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  215:              blk.9.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  216:              blk.9.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  217:                    output.weight q6_K     [  4096, 32000,     1,     1 ]\n",
            "llama_model_loader: - tensor  218:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  219:           blk.24.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  220:           blk.24.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  221:             blk.24.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  222:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  223:             blk.24.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  224:        blk.24.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  225:             blk.24.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  226:             blk.24.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  227:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  228:           blk.25.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  229:           blk.25.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  230:             blk.25.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  231:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  232:             blk.25.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  233:        blk.25.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  234:             blk.25.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  235:             blk.25.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  236:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  237:           blk.26.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  238:           blk.26.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  239:             blk.26.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  240:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  241:             blk.26.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  242:        blk.26.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  243:             blk.26.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  244:             blk.26.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  245:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  246:           blk.27.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  247:           blk.27.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  248:             blk.27.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  249:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  250:             blk.27.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  251:        blk.27.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  252:             blk.27.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  253:             blk.27.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  254:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  255:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  256:           blk.28.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  257:             blk.28.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  258:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  259:             blk.28.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  260:        blk.28.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  261:             blk.28.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  262:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  263:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  264:           blk.29.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  265:           blk.29.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  266:             blk.29.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  267:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  268:             blk.29.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  269:        blk.29.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  270:             blk.29.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  271:             blk.29.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  272:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  273:           blk.30.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  274:           blk.30.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  275:             blk.30.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  276:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  277:             blk.30.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  278:        blk.30.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  279:             blk.30.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  280:             blk.30.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  281:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  282:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  283:           blk.31.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  284:             blk.31.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  285:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  286:             blk.31.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  287:        blk.31.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  288:             blk.31.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  289:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  290:          blk.32.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  291:           blk.32.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  292:           blk.32.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  293:             blk.32.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  294:           blk.32.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  295:             blk.32.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  296:        blk.32.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  297:             blk.32.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  298:             blk.32.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  299:          blk.33.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  300:           blk.33.ffn_down.weight q5_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  301:           blk.33.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  302:             blk.33.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  303:           blk.33.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  304:             blk.33.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  305:        blk.33.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  306:             blk.33.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  307:             blk.33.attn_v.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  308:          blk.34.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  309:           blk.34.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  310:           blk.34.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  311:             blk.34.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  312:           blk.34.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  313:             blk.34.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  314:        blk.34.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  315:             blk.34.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  316:             blk.34.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  317:          blk.35.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  318:           blk.35.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  319:           blk.35.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  320:             blk.35.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  321:           blk.35.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  322:             blk.35.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  323:        blk.35.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  324:             blk.35.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  325:             blk.35.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  326:          blk.36.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  327:           blk.36.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  328:           blk.36.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  329:             blk.36.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  330:           blk.36.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  331:             blk.36.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  332:        blk.36.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  333:             blk.36.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  334:             blk.36.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  335:          blk.37.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  336:           blk.37.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  337:           blk.37.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  338:             blk.37.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  339:           blk.37.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  340:             blk.37.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  341:        blk.37.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  342:             blk.37.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  343:             blk.37.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  344:          blk.38.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  345:           blk.38.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  346:           blk.38.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  347:             blk.38.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  348:           blk.38.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  349:             blk.38.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  350:        blk.38.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  351:             blk.38.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  352:             blk.38.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  353:          blk.39.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  354:           blk.39.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  355:           blk.39.ffn_gate.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  356:             blk.39.ffn_up.weight q5_K     [  4096, 11008,     1,     1 ]\n",
            "llama_model_loader: - tensor  357:           blk.39.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  358:             blk.39.attn_k.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  359:        blk.39.attn_output.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  360:             blk.39.attn_q.weight q5_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  361:             blk.39.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
            "llama_model_loader: - tensor  362:               output_norm.weight f32      [  4096,     1,     1,     1 ]\n",
            "llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.\n",
            "llama_model_loader: - kv   0:                       general.architecture str              = llama\n",
            "llama_model_loader: - kv   1:                               general.name str              = LLaMA v2\n",
            "llama_model_loader: - kv   2:                       llama.context_length u32              = 4096\n",
            "llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096\n",
            "llama_model_loader: - kv   4:                          llama.block_count u32              = 40\n",
            "llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 11008\n",
            "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128\n",
            "llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32\n",
            "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 32\n",
            "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010\n",
            "llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 10000.000000\n",
            "llama_model_loader: - kv  11:                          general.file_type u32              = 17\n",
            "llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama\n",
            "llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,32000]   = [\"<unk>\", \"<s>\", \"</s>\", \"<0x00>\", \"<...\n",
            "llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...\n",
            "llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...\n",
            "llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 1\n",
            "llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 2\n",
            "llama_model_loader: - kv  18:            tokenizer.ggml.padding_token_id u32              = 0\n",
            "llama_model_loader: - kv  19:               tokenizer.ggml.add_bos_token bool             = true\n",
            "llama_model_loader: - kv  20:               tokenizer.ggml.add_eos_token bool             = false\n",
            "llama_model_loader: - kv  21:               general.quantization_version u32              = 2\n",
            "llama_model_loader: - type  f32:   81 tensors\n",
            "llama_model_loader: - type q5_K:  241 tensors\n",
            "llama_model_loader: - type q6_K:   41 tensors\n",
            "llm_load_vocab: special tokens definition check successful ( 259/32000 ).\n",
            "llm_load_print_meta: format           = GGUF V3 (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_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          = 40\n",
            "llm_load_print_meta: n_rot            = 128\n",
            "llm_load_print_meta: n_gqa            = 1\n",
            "llm_load_print_meta: f_norm_eps       = 0.0e+00\n",
            "llm_load_print_meta: f_norm_rms_eps   = 1.0e-05\n",
            "llm_load_print_meta: f_clamp_kqv      = 0.0e+00\n",
            "llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
            "llm_load_print_meta: n_ff             = 11008\n",
            "llm_load_print_meta: n_expert         = 0\n",
            "llm_load_print_meta: n_expert_used    = 0\n",
            "llm_load_print_meta: rope scaling     = linear\n",
            "llm_load_print_meta: freq_base_train  = 10000.0\n",
            "llm_load_print_meta: freq_scale_train = 1\n",
            "llm_load_print_meta: n_yarn_orig_ctx  = 4096\n",
            "llm_load_print_meta: rope_finetuned   = unknown\n",
            "llm_load_print_meta: model type       = 13B\n",
            "llm_load_print_meta: model ftype      = Q5_K - Medium\n",
            "llm_load_print_meta: model params     = 8.36 B\n",
            "llm_load_print_meta: model size       = 5.52 GiB (5.68 BPW) \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: PAD token        = 0 '<unk>'\n",
            "llm_load_print_meta: LF token         = 13 '<0x0A>'\n",
            "llm_load_tensors: ggml ctx size =    0.14 MiB\n",
            "llm_load_tensors: using CUDA for GPU acceleration\n",
            "llm_load_tensors: mem required  =   86.08 MiB\n",
            "llm_load_tensors: offloading 40 repeating layers to GPU\n",
            "llm_load_tensors: offloading non-repeating layers to GPU\n",
            "llm_load_tensors: offloaded 41/41 layers to GPU\n",
            "llm_load_tensors: VRAM used: 5568.02 MiB\n",
            "...................................................................................................\n",
            "llama_new_context_with_model: n_ctx      = 4096\n",
            "llama_new_context_with_model: freq_base  = 10000.0\n",
            "llama_new_context_with_model: freq_scale = 1\n",
            "llama_kv_cache_init: VRAM kv self = 2560.00 MB\n",
            "llama_new_context_with_model: KV self size  = 2560.00 MiB, K (f16): 1280.00 MiB, V (f16): 1280.00 MiB\n",
            "llama_build_graph: non-view tensors processed: 844/844\n",
            "llama_new_context_with_model: compute buffer total size = 291.19 MiB\n",
            "llama_new_context_with_model: VRAM scratch buffer: 288.00 MiB\n",
            "llama_new_context_with_model: total VRAM used: 8416.03 MiB (model: 5568.02 MiB, context: 2848.00 MiB)\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",
            "\u001b[2;36m09:21:54-452036\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m LOADER: llama.cpp                                                          \n",
            "\u001b[2;36m09:21:54-458083\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m TRUNCATION LENGTH: \u001b[1;36m4096\u001b[0m                                                    \n",
            "\u001b[2;36m09:21:54-459596\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m INSTRUCTION TEMPLATE: Alpaca                                               \n",
            "\u001b[2;36m09:21:54-460867\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Loaded the model in \u001b[1;36m25.50\u001b[0m seconds.                                         \n",
            "\u001b[2;36m09:21:54-462418\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Loading the extension \u001b[32m\"gallery\"\u001b[0m                                            \n",
            "Running on local URL:  http://127.0.0.1:7860\n",
            "Running on public URL: https://e77a8d147e3b59cb27.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 =     460.99 ms\n",
            "llama_print_timings:      sample time =      12.84 ms /    26 runs   (    0.49 ms per token,  2025.08 tokens per second)\n",
            "llama_print_timings: prompt eval time =     460.88 ms /    33 tokens (   13.97 ms per token,    71.60 tokens per second)\n",
            "llama_print_timings:        eval time =     810.28 ms /    25 runs   (   32.41 ms per token,    30.85 tokens per second)\n",
            "llama_print_timings:       total time =    1361.61 ms\n",
            "Output generated in 1.90 seconds (13.18 tokens/s, 25 tokens, context 33, seed 1294910732)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =     460.99 ms\n",
            "llama_print_timings:      sample time =      16.14 ms /    30 runs   (    0.54 ms per token,  1859.20 tokens per second)\n",
            "llama_print_timings: prompt eval time =     355.12 ms /    32 tokens (   11.10 ms per token,    90.11 tokens per second)\n",
            "llama_print_timings:        eval time =     947.85 ms /    29 runs   (   32.68 ms per token,    30.60 tokens per second)\n",
            "llama_print_timings:       total time =    1412.33 ms\n",
            "Output generated in 1.96 seconds (14.78 tokens/s, 29 tokens, context 33, seed 240923837)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =     460.99 ms\n",
            "llama_print_timings:      sample time =      57.29 ms /   106 runs   (    0.54 ms per token,  1850.30 tokens per second)\n",
            "llama_print_timings: prompt eval time =     355.59 ms /    24 tokens (   14.82 ms per token,    67.49 tokens per second)\n",
            "llama_print_timings:        eval time =    3476.83 ms /   105 runs   (   33.11 ms per token,    30.20 tokens per second)\n",
            "llama_print_timings:       total time =    4247.83 ms\n",
            "Output generated in 4.79 seconds (21.91 tokens/s, 105 tokens, context 34, seed 2049146870)\n",
            "Llama.generate: prefix-match hit\n",
            "Output generated in 18.09 seconds (23.99 tokens/s, 434 tokens, context 33, seed 1211443457)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =     460.99 ms\n",
            "llama_print_timings:      sample time =      83.91 ms /   148 runs   (    0.57 ms per token,  1763.84 tokens per second)\n",
            "llama_print_timings: prompt eval time =       0.00 ms /     1 tokens (    0.00 ms per token,      inf tokens per second)\n",
            "llama_print_timings:        eval time =    5066.53 ms /   148 runs   (   34.23 ms per token,    29.21 tokens per second)\n",
            "llama_print_timings:       total time =    5685.14 ms\n",
            "Output generated in 6.25 seconds (23.52 tokens/s, 147 tokens, context 32, seed 1886747040)\n"
          ]
        }
      ],
      "source": [
        "%cd /content\n",
        "!apt-get -y install -qq aria2\n",
        "\n",
        "!git clone -b V20231221 https://github.com/Troyanovsky/text-generation-webui\n",
        "%cd /content/text-generation-webui\n",
        "!pip install -r requirements.txt\n",
        "!pip install -U gradio==3.50.2\n",
        "\n",
        "!pip uninstall -y llama-cpp-python -y\n",
        "!CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir\n",
        "\n",
        "!pip uninstall flash-attn -y\n",
        "!pip install --no-build-isolation flash-attn==2.3.4\n",
        "\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/TheBloke/LLaMA-Pro-8B-GGUF/resolve/main/llama-pro-8b.Q5_K_M.gguf?download=true -d /content/text-generation-webui/models/ -o llama-pro-8b.Q5_K_M.gguf\n",
        "\n",
        "%cd /content/text-generation-webui\n",
        "!python server.py --share --n-gpu-layers 1000000 --model llama-pro-8b.Q5_K_M.gguf"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMP5u03hJbL41xSMid1lv2F",
      "include_colab_link": true
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}