Orca_2_13B_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/Orca_2_13B_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": [
        "## Orca-2-13B-GGUF WebUI\n",
        "1. Run the following cell, takes ~5 min\n",
        "(You may need to confirm to proceed by typing \"Y\")\n",
        "2. Click the gradio link at the bottom\n",
        "3. In Chat settings - Instruction Template: ChatML\n",
        "\n",
        "```\n",
        "<|im_start|>system\n",
        "{system_message}<|im_end|>\n",
        "<|im_start|>user\n",
        "{prompt}<|im_end|>\n",
        "<|im_start|>assistant\n",
        "```"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "D-MiHp_bveP6",
        "outputId": "4752fd09-b9ff-49e0-ed44-27df01341d9e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content\n",
            "Selecting previously unselected package libc-ares2:amd64.\n",
            "(Reading database ... 120880 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/libtbbbind_2_5.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_0.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/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",
            "Cloning into 'text-generation-webui'...\n",
            "remote: Enumerating objects: 14344, done.\u001b[K\n",
            "remote: Counting objects: 100% (1811/1811), done.\u001b[K\n",
            "remote: Compressing objects: 100% (290/290), done.\u001b[K\n",
            "remote: Total 14344 (delta 1613), reused 1643 (delta 1520), pack-reused 12533\u001b[K\n",
            "Receiving objects: 100% (14344/14344), 25.74 MiB | 9.51 MiB/s, done.\n",
            "Resolving deltas: 100% (9925/9925), done.\n",
            "Note: switching to '51add248c8a7080c3220ce16012a9f11e71f69ac'.\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",
            "Collecting git+https://github.com/oobabooga/torch-grammar.git (from -r requirements.txt (line 23))\n",
            "  Cloning https://github.com/oobabooga/torch-grammar.git to /tmp/pip-req-build-7riyqsug\n",
            "  Running command git clone --filter=blob:none --quiet https://github.com/oobabooga/torch-grammar.git /tmp/pip-req-build-7riyqsug\n",
            "  Resolved https://github.com/oobabooga/torch-grammar.git to commit 82850b5383a629f3b0fa1fba7d8f2aba3185ddb2\n",
            "  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "Ignoring 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==0.2.19+cpuavx2 (from -r requirements.txt (line 31))\n",
            "  Downloading https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.19+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl (2.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m26.6 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 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==0.5.1+cu121 (from -r requirements.txt (line 45))\n",
            "  Downloading https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+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[31m86.4 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 53))\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[31m44.7 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==0.0.8+cu121 (from -r requirements.txt (line 61))\n",
            "  Downloading https://github.com/turboderp/exllamav2/releases/download/v0.0.8/exllamav2-0.0.8+cu121-cp310-cp310-linux_x86_64.whl (12.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.3/12.3 MB\u001b[0m \u001b[31m104.8 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 69))\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[31m10.7 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 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==0.2.19+cu121 (from -r requirements.txt (line 77))\n",
            "  Downloading https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.19+cu121-cp310-cp310-manylinux_2_31_x86_64.whl (25.3 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m25.3/25.3 MB\u001b[0m \u001b[31m54.8 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 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 85))\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[31m65.3 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 88))\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[31m90.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting accelerate==0.24.* (from -r requirements.txt (line 1))\n",
            "  Downloading accelerate-0.24.1-py3-none-any.whl (261 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m261.4/261.4 kB\u001b[0m \u001b[31m6.0 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-2.15.0-py3-none-any.whl (521 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m521.2/521.2 kB\u001b[0m \u001b[31m36.7 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[31m6.2 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[31m86.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: markdown in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 7)) (3.5.1)\n",
            "Collecting numpy==1.24.* (from -r requirements.txt (line 8))\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[31m72.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting optimum==1.14.0 (from -r requirements.txt (line 9))\n",
            "  Downloading optimum-1.14.0-py3-none-any.whl (398 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m398.9/398.9 kB\u001b[0m \u001b[31m1.5 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 10)) (1.5.3)\n",
            "Collecting peft==0.6.* (from -r requirements.txt (line 11))\n",
            "  Downloading peft-0.6.2-py3-none-any.whl (174 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m174.7/174.7 kB\u001b[0m \u001b[31m24.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting Pillow>=9.5.0 (from -r requirements.txt (line 12))\n",
            "  Downloading Pillow-10.1.0-cp310-cp310-manylinux_2_28_x86_64.whl (3.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m109.6 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 13)) (6.0.1)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 14)) (2.31.0)\n",
            "Requirement already satisfied: safetensors==0.4.0 in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 15)) (0.4.0)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 16)) (1.11.3)\n",
            "Collecting sentencepiece (from -r requirements.txt (line 17))\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[31m88.6 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 18)) (2.14.1)\n",
            "Requirement already satisfied: transformers==4.35.* in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 19)) (4.35.2)\n",
            "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 20)) (4.66.1)\n",
            "Collecting wandb (from -r requirements.txt (line 21))\n",
            "  Downloading wandb-0.16.0-py3-none-any.whl (2.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m87.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting bitsandbytes==0.41.1 (from -r requirements.txt (line 26))\n",
            "  Downloading bitsandbytes-0.41.1-py3-none-any.whl (92.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.6/92.6 MB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting autoawq==0.1.7 (from -r requirements.txt (line 89))\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[31m98.0 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==0.24.*->-r requirements.txt (line 1)) (23.2)\n",
            "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate==0.24.*->-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==0.24.*->-r requirements.txt (line 1)) (2.1.0+cu118)\n",
            "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate==0.24.*->-r requirements.txt (line 1)) (0.19.4)\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-0.104.1-py3-none-any.whl (92 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.9/92.9 kB\u001b[0m \u001b[31m14.2 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[31m33.4 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-0.25.2-py3-none-any.whl (74 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.0/75.0 kB\u001b[0m \u001b[31m10.9 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[31m17.8 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[31m7.0 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-0.24.0.post1-py3-none-any.whl (59 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m59.7/59.7 kB\u001b[0m \u001b[31m7.6 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[31m17.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting coloredlogs (from optimum==1.14.0->-r requirements.txt (line 9))\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[31m6.1 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==1.14.0->-r requirements.txt (line 9)) (1.12)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.35.*->-r requirements.txt (line 19)) (3.13.1)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.35.*->-r requirements.txt (line 19)) (2023.6.3)\n",
            "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers==4.35.*->-r requirements.txt (line 19)) (0.15.0)\n",
            "Collecting lm-eval (from autoawq==0.1.7->-r requirements.txt (line 89))\n",
            "  Downloading lm_eval-0.3.0-py3-none-any.whl (178 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m178.7/178.7 kB\u001b[0m \u001b[31m22.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting texttable (from autoawq==0.1.7->-r requirements.txt (line 89))\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 89)) (0.10.2)\n",
            "Collecting attributedict (from autoawq==0.1.7->-r requirements.txt (line 89))\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 89)) (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 89)) (0.16.0+cu118)\n",
            "Requirement already satisfied: tabulate in /usr/local/lib/python3.10/dist-packages (from autoawq==0.1.7->-r requirements.txt (line 89)) (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)) (9.0.0)\n",
            "Collecting pyarrow-hotfix (from datasets->-r requirements.txt (line 3))\n",
            "  Downloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\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[31m17.1 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[31m16.3 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)) (3.8.6)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 10)) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 10)) (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 14)) (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 14)) (3.4)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 14)) (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 14)) (2023.7.22)\n",
            "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 18)) (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 18)) (1.59.2)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 18)) (2.17.3)\n",
            "Requirement already satisfied: google-auth-oauthlib<1.1,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 18)) (1.0.0)\n",
            "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 18)) (67.7.2)\n",
            "Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 18)) (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 18)) (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 18)) (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 21)) (8.1.7)\n",
            "Collecting GitPython!=3.1.29,>=1.0.0 (from wandb->-r requirements.txt (line 21))\n",
            "  Downloading GitPython-3.1.40-py3-none-any.whl (190 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m190.6/190.6 kB\u001b[0m \u001b[31m20.7 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 21))\n",
            "  Downloading sentry_sdk-1.37.1-py2.py3-none-any.whl (251 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m251.7/251.7 kB\u001b[0m \u001b[31m18.7 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 21))\n",
            "  Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\n",
            "Collecting setproctitle (from wandb->-r requirements.txt (line 21))\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 21)) (1.4.4)\n",
            "Requirement already satisfied: diskcache>=5.6.1 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python==0.2.19+cpuavx2->-r requirements.txt (line 31)) (5.6.3)\n",
            "Collecting rouge (from auto-gptq==0.5.1+cu121->-r requirements.txt (line 45))\n",
            "  Downloading rouge-1.0.1-py3-none-any.whl (13 kB)\n",
            "Collecting gekko (from auto-gptq==0.5.1+cu121->-r requirements.txt (line 45))\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[31m86.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting ninja (from exllamav2==0.0.8+cu121->-r requirements.txt (line 61))\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[31m35.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting fastparquet (from exllamav2==0.0.8+cu121->-r requirements.txt (line 61))\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[31m71.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pygments in /usr/local/lib/python3.10/dist-packages (from exllamav2==0.0.8+cu121->-r requirements.txt (line 61)) (2.16.1)\n",
            "Requirement 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 88)) (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)) (23.1.0)\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: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 3)) (4.0.3)\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)) (1.9.2)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 3)) (1.4.0)\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",
            "Collecting gitdb<5,>=4.0.1 (from GitPython!=3.1.29,>=1.0.0->wandb->-r requirements.txt (line 21))\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[31m9.6 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 18)) (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 18)) (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 18)) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<1.1,>=0.5->tensorboard->-r requirements.txt (line 18)) (1.3.1)\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)) (4.44.3)\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==0.24.*->-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==0.24.*->-r requirements.txt (line 1)) (2.1.0)\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[31m8.6 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 89))\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 89))\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 89))\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 89))\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[31m11.9 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 89))\n",
            "  Downloading tox-4.11.4-py3-none-any.whl (153 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.0/154.0 kB\u001b[0m \u001b[31m22.8 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 89))\n",
            "  Downloading coverage-7.3.2-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (227 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.5/227.5 kB\u001b[0m \u001b[31m26.8 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 89))\n",
            "  Downloading codecov-2.1.13-py2.py3-none-any.whl (16 kB)\n",
            "Collecting humanfriendly>=9.1 (from coloredlogs->optimum==1.14.0->-r requirements.txt (line 9))\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[31m11.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: anyio<4.0.0,>=3.7.1 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio==3.50.*->-r requirements.txt (line 6)) (3.7.1)\n",
            "Collecting starlette<0.28.0,>=0.27.0 (from fastapi->gradio==3.50.*->-r requirements.txt (line 6))\n",
            "  Downloading starlette-0.27.0-py3-none-any.whl (66 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.0/67.0 kB\u001b[0m \u001b[31m9.5 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-4.8.0-py3-none-any.whl (31 kB)\n",
            "Collecting cramjam>=2.3 (from fastparquet->exllamav2==0.0.8+cu121->-r requirements.txt (line 61))\n",
            "  Downloading cramjam-2.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m87.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting 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[31m11.9 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 jsonlines (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 89))\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 89)) (2.8.7)\n",
            "Collecting openai>=0.6.4 (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 89))\n",
            "  Downloading openai-1.3.6-py3-none-any.whl (220 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m220.9/220.9 kB\u001b[0m \u001b[31m25.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pybind11>=2.6.2 (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 89))\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[31m28.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pycountry (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 89))\n",
            "  Downloading pycountry-22.3.5.tar.gz (10.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.1/10.1 MB\u001b[0m \u001b[31m122.2 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 pytablewriter (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 89))\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[31m15.9 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 89))\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 89))\n",
            "  Downloading sacrebleu-1.5.0-py3-none-any.whl (65 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m65.6/65.6 kB\u001b[0m \u001b[31m8.3 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 89)) (1.2.2)\n",
            "Collecting sqlitedict (from lm-eval->autoawq==0.1.7->-r requirements.txt (line 89))\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 89))\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 89))\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[31m81.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting portalocker (from sacrebleu==1.5.0->lm-eval->autoawq==0.1.7->-r requirements.txt (line 89))\n",
            "  Downloading portalocker-2.8.2-py3-none-any.whl (17 kB)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->optimum==1.14.0->-r requirements.txt (line 9)) (1.3.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<4.0.0,>=3.7.1->fastapi->gradio==3.50.*->-r requirements.txt (line 6)) (1.1.3)\n",
            "Collecting blessings (from colour-runner>=0.0.5->attributedict->autoawq==0.1.7->-r requirements.txt (line 89))\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 89))\n",
            "  Downloading ordered_set-4.1.0-py3-none-any.whl (7.6 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 21))\n",
            "  Downloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
            "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from inspecta>=0.1.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 89)) (2.3.0)\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.*->-r requirements.txt (line 6)) (2023.11.1)\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)) (0.31.0)\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)) (0.13.0)\n",
            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai>=0.6.4->lm-eval->autoawq==0.1.7->-r requirements.txt (line 89)) (1.7.0)\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 18)) (0.5.0)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<1.1,>=0.5->tensorboard->-r requirements.txt (line 18)) (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 89)) (3.8.1)\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 89)) (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 89)) (3.2.0)\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 89)) (5.2.0)\n",
            "Requirement already satisfied: platformdirs>=3.10 in /usr/local/lib/python3.10/dist-packages (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 89)) (4.0.0)\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 89)) (1.3.0)\n",
            "Collecting pyproject-api>=1.6.1 (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 89))\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 89)) (2.0.1)\n",
            "Collecting virtualenv>=20.24.3 (from tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 89))\n",
            "  Downloading virtualenv-20.24.7-py3-none-any.whl (3.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.8/3.8 MB\u001b[0m \u001b[31m127.4 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 89))\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 89))\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 89))\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 89))\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 89))\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 89))\n",
            "  Downloading typepy-1.3.2-py3-none-any.whl (31 kB)\n",
            "Collecting distlib<1,>=0.3.7 (from virtualenv>=20.24.3->tox>=3.0.0->attributedict->autoawq==0.1.7->-r requirements.txt (line 89))\n",
            "  Downloading distlib-0.3.7-py2.py3-none-any.whl (468 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m468.9/468.9 kB\u001b[0m \u001b[31m48.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hBuilding wheels for collected packages: torch-grammar, ffmpy, rouge-score, pycountry, sqlitedict\n",
            "  Building wheel for torch-grammar (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for torch-grammar: filename=torch_grammar-0.3.3-py3-none-any.whl size=8259 sha256=43be34776231fd2667ba9ad3979c115c48a2c24c75a4393f0ef4f4ac2379d364\n",
            "  Stored in directory: /tmp/pip-ephem-wheel-cache-8d1j2jm3/wheels/dd/00/c9/08292a4496a8b7e174aefc6e0a8194cbb53977b7cbdd3006b7\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=ab207fc7c96f16b41983e151ab44a3d60b459803b18334514bc97abda813fe60\n",
            "  Stored in directory: /root/.cache/pip/wheels/01/a6/d1/1c0828c304a4283b2c1639a09ad86f83d7c487ef34c6b4a1bf\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=f8ad0c8a9becd01a8a6988807f1bdd4fc0144ae7c0339c113e472c0aea023cf6\n",
            "  Stored in directory: /root/.cache/pip/wheels/5f/dd/89/461065a73be61a532ff8599a28e9beef17985c9e9c31e541b4\n",
            "  Building wheel for pycountry (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for pycountry: filename=pycountry-22.3.5-py2.py3-none-any.whl size=10681832 sha256=f91a53d5597278b16b6cf538d2fe16e72dede5c58ee7018368b92be288f794c7\n",
            "  Stored in directory: /root/.cache/pip/wheels/03/57/cc/290c5252ec97a6d78d36479a3c5e5ecc76318afcb241ad9dbe\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=b0d732f16b183685cb6cdf1b27473e552b27b01ec883415386660ef7b641d51e\n",
            "  Stored in directory: /root/.cache/pip/wheels/79/d6/e7/304e0e6cb2221022c26d8161f7c23cd4f259a9e41e8bbcfabd\n",
            "Successfully built torch-grammar ffmpy rouge-score pycountry 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, pycountry, pybind11, pyarrow-hotfix, 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, multiprocess, 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, openai, inspecta, gradio-client, exllamav2, datasets, DataProperty, torch-grammar, tabledata, peft, gradio, 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",
            "\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",
            "llmx 0.0.15a0 requires cohere, which is not installed.\n",
            "llmx 0.0.15a0 requires tiktoken, which is not installed.\n",
            "imageio 2.31.6 requires pillow<10.1.0,>=8.3.2, but you have pillow 10.1.0 which is incompatible.\n",
            "tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.8.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed DataProperty-1.0.1 GitPython-3.1.40 Pillow-10.1.0 accelerate-0.24.1 aiofiles-23.2.1 attributedict-0.3.0 auto-gptq-0.5.1+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-7.3.2 cramjam-2.7.0 ctransformers-0.2.27+cu121 datasets-2.15.0 deepdiff-6.7.1 dill-0.3.7 distlib-0.3.7 docker-pycreds-0.4.0 einops-0.7.0 exllama-0.0.18+cu121 exllamav2-0.0.8+cu121 fastapi-0.104.1 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 httpcore-1.0.2 httpx-0.25.2 humanfriendly-10.0 inspecta-0.1.3 jsonlines-4.0.0 llama-cpp-python-0.2.19+cpuavx2 llama-cpp-python-cuda-0.2.19+cu121 lm-eval-0.3.0 mbstrdecoder-1.1.3 multiprocess-0.70.15 ninja-1.11.1.1 numpy-1.24.4 openai-1.3.6 optimum-1.14.0 ordered-set-4.1.0 orjson-3.9.10 pathvalidate-3.2.0 peft-0.6.2 portalocker-2.8.2 pyarrow-hotfix-0.6 pybind11-2.11.1 pycountry-22.3.5 pydub-0.25.1 pyproject-api-1.6.1 pytablewriter-1.2.0 python-multipart-0.0.6 rootpath-0.1.1 rouge-1.0.1 rouge-score-0.1.2 sacrebleu-1.5.0 semantic-version-2.10.0 sentencepiece-0.1.99 sentry-sdk-1.37.1 setproctitle-1.3.3 smmap-5.0.1 sqlitedict-2.1.0 starlette-0.27.0 tabledata-1.3.3 tcolorpy-0.1.4 texttable-1.7.0 torch-grammar-0.3.3 tox-4.11.4 tqdm-multiprocess-0.0.11 typepy-1.3.2 typing-extensions-4.8.0 uvicorn-0.24.0.post1 virtualenv-20.24.7 wandb-0.16.0 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) (0.104.1)\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) (0.25.2)\n",
            "Requirement already satisfied: huggingface-hub>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.19.4)\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) (10.1.0)\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) (4.8.0)\n",
            "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==3.50.2) (0.24.0.post1)\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) (4.44.3)\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) (3.4)\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) (2023.7.22)\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: anyio<4.0.0,>=3.7.1 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio==3.50.2) (3.7.1)\n",
            "Requirement already satisfied: starlette<0.28.0,>=0.27.0 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio==3.50.2) (0.27.0)\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: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<4.0.0,>=3.7.1->fastapi->gradio==3.50.2) (1.1.3)\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) (23.1.0)\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) (2023.11.1)\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) (0.31.0)\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) (0.13.0)\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",
            "Found existing installation: llama_cpp_python 0.2.19+cpuavx2\n",
            "Uninstalling llama_cpp_python-0.2.19+cpuavx2:\n",
            "  Successfully uninstalled llama_cpp_python-0.2.19+cpuavx2\n",
            "Collecting llama-cpp-python\n",
            "  Downloading llama_cpp_python-0.2.20.tar.gz (8.7 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.7/8.7 MB\u001b[0m \u001b[31m131.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
            "  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) (4.8.0)\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-0.2.20-cp310-cp310-manylinux_2_35_x86_64.whl size=7138116 sha256=d2a16bd59369cf45761d345275bbc4ed79f097974daa2ef57c29fd9ea5bc4113\n",
            "  Stored in directory: /tmp/pip-ephem-wheel-cache-95x6z3r4/wheels/ef/f2/d2/0becb03047a348d7bd9a5b91ec88f4654d6fa7d67ea4e84d43\n",
            "Successfully built llama-cpp-python\n",
            "Installing collected packages: llama-cpp-python\n",
            "Successfully installed llama-cpp-python-0.2.20\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[31m37.4 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+cu118)\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) (4.8.0)\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=57449248 sha256=4ceff7f9ad6a6747975b568f3193b2416f598808b5e860fb09555dbfa32b42cf\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",
            "f16e4a|\u001b[1;32mOK\u001b[0m  |   171MiB/s|/content/text-generation-webui/models//orca-2-13b.Q5_K_M.gguf\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "/content/text-generation-webui\n",
            "2023-11-29 07:19:34 INFO:\u001b[32mLoading orca-2-13b.Q5_K_M.gguf...\u001b[0m\n",
            "2023-11-29 07:19:34 INFO:\u001b[32mllama.cpp weights detected: models/orca-2-13b.Q5_K_M.gguf\u001b[0m\n",
            "2023-11-29 07:19:34 INFO:\u001b[32mCache capacity is 0 bytes\u001b[0m\n",
            "ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no\n",
            "ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes\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/orca-2-13b.Q5_K_M.gguf (version GGUF V3 (latest))\n",
            "llama_model_loader: - tensor    0:                token_embd.weight q5_K     [  5120, 32003,     1,     1 ]\n",
            "llama_model_loader: - tensor    1:              blk.0.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor    2:              blk.0.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor    3:              blk.0.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor    4:         blk.0.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor    5:            blk.0.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor    6:              blk.0.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor    7:            blk.0.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor    8:           blk.0.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor    9:            blk.0.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   10:              blk.1.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   11:              blk.1.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   12:              blk.1.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   13:         blk.1.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   14:            blk.1.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   15:              blk.1.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   16:            blk.1.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   17:           blk.1.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   18:            blk.1.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   19:              blk.2.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   20:              blk.2.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   21:              blk.2.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   22:         blk.2.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   23:            blk.2.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   24:              blk.2.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   25:            blk.2.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   26:           blk.2.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   27:            blk.2.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   28:              blk.3.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   29:              blk.3.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   30:              blk.3.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   31:         blk.3.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   32:            blk.3.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   33:              blk.3.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   34:            blk.3.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   35:           blk.3.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   36:            blk.3.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   37:              blk.4.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   38:              blk.4.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   39:              blk.4.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   40:         blk.4.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   41:            blk.4.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   42:              blk.4.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   43:            blk.4.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   44:           blk.4.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   45:            blk.4.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   46:              blk.5.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   47:              blk.5.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   48:              blk.5.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   49:         blk.5.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   50:            blk.5.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   51:              blk.5.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   52:            blk.5.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   53:           blk.5.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   54:            blk.5.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   55:              blk.6.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   56:              blk.6.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   57:              blk.6.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   58:         blk.6.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   59:            blk.6.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   60:              blk.6.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   61:            blk.6.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   62:           blk.6.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   63:            blk.6.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   64:              blk.7.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   65:              blk.7.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   66:              blk.7.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   67:         blk.7.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   68:            blk.7.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   69:              blk.7.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   70:            blk.7.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   71:           blk.7.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   72:            blk.7.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   73:              blk.8.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   74:              blk.8.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   75:              blk.8.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   76:         blk.8.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   77:            blk.8.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   78:              blk.8.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   79:            blk.8.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   80:           blk.8.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   81:            blk.8.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   82:              blk.9.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   83:              blk.9.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   84:              blk.9.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   85:         blk.9.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   86:            blk.9.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   87:              blk.9.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   88:            blk.9.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   89:           blk.9.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   90:            blk.9.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   91:             blk.10.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   92:             blk.10.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   93:             blk.10.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   94:        blk.10.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   95:           blk.10.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   96:             blk.10.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor   97:           blk.10.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor   98:          blk.10.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor   99:           blk.10.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  100:             blk.11.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  101:             blk.11.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  102:             blk.11.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  103:        blk.11.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  104:           blk.11.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  105:             blk.11.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  106:           blk.11.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  107:          blk.11.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  108:           blk.11.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  109:             blk.12.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  110:             blk.12.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  111:             blk.12.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  112:        blk.12.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  113:           blk.12.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  114:             blk.12.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  115:           blk.12.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  116:          blk.12.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  117:           blk.12.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  118:             blk.13.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  119:             blk.13.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  120:             blk.13.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  121:        blk.13.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  122:           blk.13.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  123:             blk.13.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  124:           blk.13.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  125:          blk.13.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  126:           blk.13.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  127:             blk.14.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  128:             blk.14.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  129:             blk.14.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  130:        blk.14.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  131:           blk.14.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  132:             blk.14.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  133:           blk.14.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  134:          blk.14.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  135:           blk.14.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  136:             blk.15.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  137:             blk.15.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  138:             blk.15.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  139:        blk.15.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  140:           blk.15.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  141:             blk.15.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  142:           blk.15.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  143:          blk.15.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  144:           blk.15.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  145:             blk.16.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  146:             blk.16.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  147:             blk.16.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  148:        blk.16.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  149:           blk.16.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  150:             blk.16.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  151:           blk.16.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  152:          blk.16.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  153:           blk.16.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  154:             blk.17.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  155:             blk.17.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  156:             blk.17.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  157:        blk.17.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  158:           blk.17.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  159:             blk.17.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  160:           blk.17.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  161:          blk.17.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  162:           blk.17.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  163:             blk.18.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  164:             blk.18.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  165:             blk.18.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  166:        blk.18.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  167:           blk.18.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  168:             blk.18.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  169:           blk.18.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  170:          blk.18.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  171:           blk.18.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  172:             blk.19.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  173:             blk.19.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  174:             blk.19.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  175:        blk.19.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  176:           blk.19.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  177:             blk.19.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  178:           blk.19.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  179:          blk.19.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  180:           blk.19.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  181:             blk.20.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  182:             blk.20.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  183:             blk.20.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  184:        blk.20.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  185:           blk.20.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  186:             blk.20.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  187:           blk.20.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  188:          blk.20.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  189:           blk.20.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  190:             blk.21.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  191:             blk.21.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  192:             blk.21.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  193:        blk.21.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  194:           blk.21.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  195:             blk.21.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  196:           blk.21.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  197:          blk.21.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  198:           blk.21.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  199:             blk.22.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  200:             blk.22.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  201:             blk.22.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  202:        blk.22.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  203:           blk.22.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  204:             blk.22.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  205:           blk.22.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  206:          blk.22.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  207:           blk.22.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  208:             blk.23.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  209:             blk.23.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  210:             blk.23.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  211:        blk.23.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  212:           blk.23.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  213:             blk.23.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  214:           blk.23.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  215:          blk.23.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  216:           blk.23.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  217:             blk.24.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  218:             blk.24.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  219:             blk.24.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  220:        blk.24.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  221:           blk.24.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  222:             blk.24.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  223:           blk.24.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  224:          blk.24.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  225:           blk.24.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  226:             blk.25.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  227:             blk.25.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  228:             blk.25.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  229:        blk.25.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  230:           blk.25.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  231:             blk.25.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  232:           blk.25.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  233:          blk.25.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  234:           blk.25.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  235:             blk.26.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  236:             blk.26.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  237:             blk.26.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  238:        blk.26.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  239:           blk.26.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  240:             blk.26.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  241:           blk.26.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  242:          blk.26.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  243:           blk.26.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  244:             blk.27.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  245:             blk.27.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  246:             blk.27.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  247:        blk.27.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  248:           blk.27.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  249:             blk.27.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  250:           blk.27.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  251:          blk.27.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  252:           blk.27.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  253:             blk.28.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  254:             blk.28.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  255:             blk.28.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  256:        blk.28.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  257:           blk.28.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  258:             blk.28.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  259:           blk.28.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  260:          blk.28.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  261:           blk.28.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  262:             blk.29.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  263:             blk.29.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  264:             blk.29.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  265:        blk.29.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  266:           blk.29.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  267:             blk.29.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  268:           blk.29.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  269:          blk.29.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  270:           blk.29.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  271:             blk.30.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  272:             blk.30.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  273:             blk.30.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  274:        blk.30.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  275:           blk.30.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  276:             blk.30.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  277:           blk.30.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  278:          blk.30.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  279:           blk.30.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  280:             blk.31.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  281:             blk.31.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  282:             blk.31.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  283:        blk.31.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  284:           blk.31.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  285:             blk.31.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  286:           blk.31.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  287:          blk.31.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  288:           blk.31.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  289:             blk.32.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  290:             blk.32.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  291:             blk.32.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  292:        blk.32.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  293:           blk.32.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  294:             blk.32.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  295:           blk.32.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  296:          blk.32.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  297:           blk.32.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  298:             blk.33.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  299:             blk.33.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  300:             blk.33.attn_v.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  301:        blk.33.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  302:           blk.33.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  303:             blk.33.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  304:           blk.33.ffn_down.weight q5_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  305:          blk.33.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  306:           blk.33.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  307:             blk.34.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  308:             blk.34.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  309:             blk.34.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  310:        blk.34.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  311:           blk.34.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  312:             blk.34.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  313:           blk.34.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  314:          blk.34.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  315:           blk.34.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  316:             blk.35.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  317:             blk.35.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  318:             blk.35.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  319:        blk.35.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  320:           blk.35.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  321:             blk.35.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  322:           blk.35.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  323:          blk.35.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  324:           blk.35.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  325:             blk.36.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  326:             blk.36.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  327:             blk.36.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  328:        blk.36.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  329:           blk.36.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  330:             blk.36.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  331:           blk.36.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  332:          blk.36.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  333:           blk.36.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  334:             blk.37.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  335:             blk.37.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  336:             blk.37.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  337:        blk.37.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  338:           blk.37.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  339:             blk.37.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  340:           blk.37.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  341:          blk.37.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  342:           blk.37.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  343:             blk.38.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  344:             blk.38.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  345:             blk.38.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  346:        blk.38.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  347:           blk.38.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  348:             blk.38.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  349:           blk.38.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  350:          blk.38.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  351:           blk.38.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  352:             blk.39.attn_q.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  353:             blk.39.attn_k.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  354:             blk.39.attn_v.weight q6_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  355:        blk.39.attn_output.weight q5_K     [  5120,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  356:           blk.39.ffn_gate.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  357:             blk.39.ffn_up.weight q5_K     [  5120, 13824,     1,     1 ]\n",
            "llama_model_loader: - tensor  358:           blk.39.ffn_down.weight q6_K     [ 13824,  5120,     1,     1 ]\n",
            "llama_model_loader: - tensor  359:          blk.39.attn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  360:           blk.39.ffn_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  361:               output_norm.weight f32      [  5120,     1,     1,     1 ]\n",
            "llama_model_loader: - tensor  362:                    output.weight q6_K     [  5120, 32003,     1,     1 ]\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              = 5120\n",
            "llama_model_loader: - kv   4:                          llama.block_count u32              = 40\n",
            "llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 13824\n",
            "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128\n",
            "llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 40\n",
            "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 40\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,32003]   = [\"<unk>\", \"<s>\", \"</s>\", \"<0x00>\", \"<...\n",
            "llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,32003]   = [0.000000, 0.000000, 0.000000, 0.0000...\n",
            "llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,32003]   = [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 ( 262/32003 ).\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          = 32003\n",
            "llm_load_print_meta: n_merges         = 0\n",
            "llm_load_print_meta: n_ctx_train      = 4096\n",
            "llm_load_print_meta: n_embd           = 5120\n",
            "llm_load_print_meta: n_head           = 40\n",
            "llm_load_print_meta: n_head_kv        = 40\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             = 13824\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      = mostly Q5_K - Medium\n",
            "llm_load_print_meta: model params     = 13.02 B\n",
            "llm_load_print_meta: model size       = 8.60 GiB (5.67 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 =    0.13 MiB\n",
            "llm_load_tensors: using CUDA for GPU acceleration\n",
            "llm_load_tensors: mem required  =  107.56 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 43/43 layers to GPU\n",
            "llm_load_tensors: VRAM used: 8694.22 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: offloading v cache to GPU\n",
            "llama_kv_cache_init: offloading k cache to GPU\n",
            "llama_kv_cache_init: VRAM kv self = 3200.00 MiB\n",
            "llama_new_context_with_model: kv self size  = 3200.00 MiB\n",
            "llama_build_graph: non-view tensors processed: 924/924\n",
            "llama_new_context_with_model: compute buffer total size = 361.07 MiB\n",
            "llama_new_context_with_model: VRAM scratch buffer: 358.00 MiB\n",
            "llama_new_context_with_model: total VRAM used: 12252.22 MiB (model: 8694.22 MiB, context: 3558.00 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",
            "2023-11-29 07:21:12 INFO:\u001b[32mTRUNCATION LENGTH: 4096\u001b[0m\n",
            "2023-11-29 07:21:12 INFO:\u001b[32mINSTRUCTION TEMPLATE: ChatML\u001b[0m\n",
            "2023-11-29 07:21:12 INFO:\u001b[32mLoaded the model in 98.55 seconds.\u001b[0m\n",
            "2023-11-29 07:21:12 INFO:\u001b[32mLoading the extension \"gallery\"...\u001b[0m\n",
            "Running on local URL:  http://127.0.0.1:7860\n",
            "Running on public URL: https://1a94819c38ae705e81.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",
            "Traceback (most recent call last):\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/gradio/queueing.py\", line 407, in call_prediction\n",
            "    output = await route_utils.call_process_api(\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/gradio/route_utils.py\", line 226, in call_process_api\n",
            "    output = await app.get_blocks().process_api(\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/gradio/blocks.py\", line 1550, in process_api\n",
            "    result = await self.call_function(\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/gradio/blocks.py\", line 1185, in call_function\n",
            "    prediction = await anyio.to_thread.run_sync(\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py\", line 33, in run_sync\n",
            "    return await get_asynclib().run_sync_in_worker_thread(\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py\", line 877, in run_sync_in_worker_thread\n",
            "    return await future\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py\", line 807, in run\n",
            "    result = context.run(func, *args)\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/gradio/utils.py\", line 661, in wrapper\n",
            "    response = f(*args, **kwargs)\n",
            "  File \"/content/text-generation-webui/modules/ui_chat.py\", line 278, in <lambda>\n",
            "    lambda x: gr.update(choices=(histories := chat.find_all_histories(x)), value=histories[0]), gradio('interface_state'), gradio('unique_id')).then(\n",
            "IndexError: list index out of range\n",
            "\n",
            "llama_print_timings:        load time =     922.44 ms\n",
            "llama_print_timings:      sample time =      41.37 ms /    83 runs   (    0.50 ms per token,  2006.09 tokens per second)\n",
            "llama_print_timings: prompt eval time =     922.30 ms /    31 tokens (   29.75 ms per token,    33.61 tokens per second)\n",
            "llama_print_timings:        eval time =    4166.66 ms /    82 runs   (   50.81 ms per token,    19.68 tokens per second)\n",
            "llama_print_timings:       total time =    5392.09 ms\n",
            "Output generated in 5.88 seconds (13.94 tokens/s, 82 tokens, context 61, seed 1669633118)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =     922.44 ms\n",
            "llama_print_timings:      sample time =      44.37 ms /    88 runs   (    0.50 ms per token,  1983.50 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 =    4433.65 ms /    88 runs   (   50.38 ms per token,    19.85 tokens per second)\n",
            "llama_print_timings:       total time =    4819.96 ms\n",
            "Output generated in 5.48 seconds (15.88 tokens/s, 87 tokens, context 61, seed 1163945151)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =     922.44 ms\n",
            "llama_print_timings:      sample time =      48.90 ms /    79 runs   (    0.62 ms per token,  1615.51 tokens per second)\n",
            "llama_print_timings: prompt eval time =     641.88 ms /    24 tokens (   26.74 ms per token,    37.39 tokens per second)\n",
            "llama_print_timings:        eval time =    4009.78 ms /    78 runs   (   51.41 ms per token,    19.45 tokens per second)\n",
            "llama_print_timings:       total time =    5066.42 ms\n",
            "Output generated in 5.58 seconds (13.98 tokens/s, 78 tokens, context 196, seed 1904430252)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =     922.44 ms\n",
            "llama_print_timings:      sample time =      39.82 ms /    71 runs   (    0.56 ms per token,  1783.16 tokens per second)\n",
            "llama_print_timings: prompt eval time =     621.58 ms /    23 tokens (   27.03 ms per token,    37.00 tokens per second)\n",
            "llama_print_timings:        eval time =    3647.12 ms /    70 runs   (   52.10 ms per token,    19.19 tokens per second)\n",
            "llama_print_timings:       total time =    4522.82 ms\n",
            "Output generated in 5.02 seconds (13.94 tokens/s, 70 tokens, context 320, seed 2060246706)\n"
          ]
        }
      ],
      "source": [
        "%cd /content\n",
        "!apt-get -y install -qq aria2\n",
        "\n",
        "!git clone -b V20231127 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/Orca-2-13B-GGUF/resolve/main/orca-2-13b.Q5_K_M.gguf?download=true -d /content/text-generation-webui/models/ -o orca-2-13b.Q5_K_M.gguf\n",
        "\n",
        "%cd /content/text-generation-webui\n",
        "!python server.py --share --n-gpu-layers 1000000000 --model orca-2-13b.Q5_K_M.gguf"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyN986tgZcGmqrDpYywZtL9Y",
      "include_colab_link": true
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}