Meta_Llama_3_8B_Instruct_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/Meta_Llama_3_8B_Instruct_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": [
        "## Meta-Llama-3-8B-Instruct-GGUF WebUI\n",
        "\n",
        "1. Run the following cell, takes ~5 min\n",
        "(You may need to confirm to proceed by typing \"Y\")\n",
        "2. Pick the version you need from one of the last two cells and only run that cell.\n",
        "3. Click the gradio link at the bottom\n",
        "4. In Parameter settings - Instruction Template:\n",
        "\n",
        "```\n",
        "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n",
        "\n",
        "{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>\n",
        "\n",
        "{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n",
        "```\n",
        "\n",
        "Original model: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct\n",
        "\n",
        "Quantized model: https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF\n",
        "\n",
        "Want to try other local LLMs? Check out this repo: https://github.com/Troyanovsky/Local-LLM-Comparison-Colab-UI/"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "background_save": true,
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "D-MiHp_bveP6",
        "outputId": "cc89a36b-0880-4044-dfcf-a99b08b4d577"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content\n",
            "Selecting previously unselected package libc-ares2:amd64.\n",
            "(Reading database ... 121752 files and directories currently installed.)\n",
            "Preparing to unpack .../libc-ares2_1.18.1-1ubuntu0.22.04.3_amd64.deb ...\n",
            "Unpacking libc-ares2:amd64 (1.18.1-1ubuntu0.22.04.3) ...\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 (1.18.1-1ubuntu0.22.04.3) ...\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/libtbb.so.12 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_0.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc_proxy.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_5.so.3 is not a symbolic link\n",
            "\n",
            "Cloning into 'text-generation-webui'...\n",
            "remote: Enumerating objects: 17493, done.\u001b[K\n",
            "remote: Counting objects: 100% (8627/8627), done.\u001b[K\n",
            "remote: Compressing objects: 100% (467/467), done.\u001b[K\n",
            "remote: Total 17493 (delta 8320), reused 8177 (delta 8159), pack-reused 8866\u001b[K\n",
            "Receiving objects: 100% (17493/17493), 26.41 MiB | 31.82 MiB/s, done.\n",
            "Resolving deltas: 100% (12478/12478), done.\n",
            "Note: switching to '26d822f64f2a029306b250b69dc58468662a4fc6'.\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 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==0.2.61+cpuavx2 (from -r requirements.txt (line 38))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.61+cpuavx2-cp310-cp310-manylinux_2_31_x86_64.whl (3.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.0/3.0 MB\u001b[0m \u001b[31m11.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring 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-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 == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting llama-cpp-python-cuda==0.2.61+cu121 (from -r requirements.txt (line 46))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.61+cu121-cp310-cp310-manylinux_2_31_x86_64.whl (86.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.4/86.4 MB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring llama-cpp-python-cuda-tensorcores: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting llama-cpp-python-cuda-tensorcores==0.2.61+cu121 (from -r requirements.txt (line 52))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.61+cu121-cp310-cp310-manylinux_2_31_x86_64.whl (73.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m73.8/73.8 MB\u001b[0m \u001b[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring 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 == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting auto-gptq==0.6.0+cu121 (from -r requirements.txt (line 58))\n",
            "  Downloading https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl (4.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.8/4.8 MB\u001b[0m \u001b[31m57.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring 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 == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting exllamav2==0.0.18+cu121 (from -r requirements.txt (line 62))\n",
            "  Downloading https://github.com/turboderp/exllamav2/releases/download/v0.0.18/exllamav2-0.0.18+cu121-cp310-cp310-linux_x86_64.whl (133.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.0/133.0 MB\u001b[0m \u001b[31m7.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring exllamav2: markers 'platform_system == \"Linux\" and platform_machine != \"x86_64\"' 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 == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting flash-attn==2.5.6+cu122torch2.2cxx11abiFALSE (from -r requirements.txt (line 67))\n",
            "  Downloading https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl (120.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m120.6/120.6 MB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring 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 == \"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 71))\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[31m64.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting accelerate==0.27.* (from -r requirements.txt (line 1))\n",
            "  Downloading accelerate-0.27.2-py3-none-any.whl (279 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m280.0/280.0 kB\u001b[0m \u001b[31m7.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting aqlm[cpu,gpu]==1.1.3 (from -r requirements.txt (line 2))\n",
            "  Downloading aqlm-1.1.3-py3-none-any.whl (14 kB)\n",
            "Collecting bitsandbytes==0.43.* (from -r requirements.txt (line 3))\n",
            "  Downloading bitsandbytes-0.43.1-py3-none-manylinux_2_24_x86_64.whl (119.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m119.8/119.8 MB\u001b[0m \u001b[31m8.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting colorama (from -r requirements.txt (line 4))\n",
            "  Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
            "Collecting datasets (from -r requirements.txt (line 5))\n",
            "  Downloading datasets-2.18.0-py3-none-any.whl (510 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m510.5/510.5 kB\u001b[0m \u001b[31m52.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting einops (from -r requirements.txt (line 6))\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[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting gradio==4.26.* (from -r requirements.txt (line 7))\n",
            "  Downloading gradio-4.26.0-py3-none-any.whl (17.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.1/17.1 MB\u001b[0m \u001b[31m80.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting hqq==0.1.5 (from -r requirements.txt (line 8))\n",
            "  Downloading hqq-0.1.5.tar.gz (31 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting jinja2==3.1.2 (from -r requirements.txt (line 9))\n",
            "  Downloading Jinja2-3.1.2-py3-none-any.whl (133 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.1/133.1 kB\u001b[0m \u001b[31m19.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting lm_eval==0.3.0 (from -r requirements.txt (line 10))\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[31m24.7 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 11)) (3.6)\n",
            "Collecting numba==0.59.* (from -r requirements.txt (line 12))\n",
            "  Downloading numba-0.59.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (3.7 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.7/3.7 MB\u001b[0m \u001b[31m100.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting numpy==1.26.* (from -r requirements.txt (line 13))\n",
            "  Downloading numpy-1.26.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.2/18.2 MB\u001b[0m \u001b[31m70.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting optimum==1.17.* (from -r requirements.txt (line 14))\n",
            "  Downloading optimum-1.17.1-py3-none-any.whl (407 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m407.1/407.1 kB\u001b[0m \u001b[31m43.0 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 15)) (2.0.3)\n",
            "Collecting peft==0.8.* (from -r requirements.txt (line 16))\n",
            "  Downloading peft-0.8.2-py3-none-any.whl (183 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m183.4/183.4 kB\u001b[0m \u001b[31m22.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting Pillow>=9.5.0 (from -r requirements.txt (line 17))\n",
            "  Downloading pillow-10.3.0-cp310-cp310-manylinux_2_28_x86_64.whl (4.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.5/4.5 MB\u001b[0m \u001b[31m96.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 18)) (5.9.5)\n",
            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 19)) (6.0.1)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 20)) (2.31.0)\n",
            "Requirement already satisfied: rich in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 21)) (13.7.1)\n",
            "Requirement already satisfied: safetensors==0.4.* in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 22)) (0.4.3)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 23)) (1.11.4)\n",
            "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 24)) (0.1.99)\n",
            "Requirement already satisfied: tensorboard in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 25)) (2.15.2)\n",
            "Collecting transformers==4.39.* (from -r requirements.txt (line 26))\n",
            "  Downloading transformers-4.39.3-py3-none-any.whl (8.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.8/8.8 MB\u001b[0m \u001b[31m98.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 27)) (4.66.2)\n",
            "Collecting wandb (from -r requirements.txt (line 28))\n",
            "  Downloading wandb-0.16.6-py3-none-any.whl (2.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m89.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting SpeechRecognition==3.10.0 (from -r requirements.txt (line 31))\n",
            "  Downloading SpeechRecognition-3.10.0-py2.py3-none-any.whl (32.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m32.8/32.8 MB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting flask_cloudflared==0.0.14 (from -r requirements.txt (line 32))\n",
            "  Downloading flask_cloudflared-0.0.14-py3-none-any.whl (6.4 kB)\n",
            "Collecting sse-starlette==2.1.0 (from -r requirements.txt (line 33))\n",
            "  Downloading sse_starlette-2.1.0-py3-none-any.whl (9.2 kB)\n",
            "Collecting tiktoken (from -r requirements.txt (line 34))\n",
            "  Downloading tiktoken-0.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m83.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting autoawq==0.2.3 (from -r requirements.txt (line 72))\n",
            "  Downloading autoawq-0.2.3-cp310-cp310-manylinux2014_x86_64.whl (79 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.0/79.0 kB\u001b[0m \u001b[31m10.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.*->-r requirements.txt (line 1)) (24.0)\n",
            "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.*->-r requirements.txt (line 1)) (2.2.1+cu121)\n",
            "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate==0.27.*->-r requirements.txt (line 1)) (0.20.3)\n",
            "Requirement already satisfied: triton>=2.1 in /usr/local/lib/python3.10/dist-packages (from aqlm[cpu,gpu]==1.1.3->-r requirements.txt (line 2)) (2.2.0)\n",
            "Collecting ninja (from aqlm[cpu,gpu]==1.1.3->-r requirements.txt (line 2))\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[31m35.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting aiofiles<24.0,>=22.0 (from gradio==4.26.*->-r requirements.txt (line 7))\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==4.26.*->-r requirements.txt (line 7)) (4.2.2)\n",
            "Collecting fastapi (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading fastapi-0.110.2-py3-none-any.whl (91 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m91.9/91.9 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting ffmpy (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading ffmpy-0.3.2.tar.gz (5.5 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Collecting gradio-client==0.15.1 (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading gradio_client-0.15.1-py3-none-any.whl (313 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m313.6/313.6 kB\u001b[0m \u001b[31m40.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting httpx>=0.24.1 (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading httpx-0.27.0-py3-none-any.whl (75 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.6/75.6 kB\u001b[0m \u001b[31m10.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 7)) (6.4.0)\n",
            "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 7)) (2.1.5)\n",
            "Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 7)) (3.7.1)\n",
            "Collecting orjson~=3.0 (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading orjson-3.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (141 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m141.1/141.1 kB\u001b[0m \u001b[31m18.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 7)) (2.7.0)\n",
            "Collecting pydub (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
            "Collecting python-multipart>=0.0.9 (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n",
            "Collecting ruff>=0.2.2 (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading ruff-0.4.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.7 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.7/8.7 MB\u001b[0m \u001b[31m80.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting semantic-version~=2.0 (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
            "Collecting tomlkit==0.12.0 (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading tomlkit-0.12.0-py3-none-any.whl (37 kB)\n",
            "Requirement already satisfied: typer[all]<1.0,>=0.9 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 7)) (0.9.4)\n",
            "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 7)) (4.11.0)\n",
            "Collecting uvicorn>=0.14.0 (from gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading uvicorn-0.29.0-py3-none-any.whl (60 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting timm (from hqq==0.1.5->-r requirements.txt (line 8))\n",
            "  Downloading timm-0.9.16-py3-none-any.whl (2.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.2/2.2 MB\u001b[0m \u001b[31m73.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: termcolor in /usr/local/lib/python3.10/dist-packages (from hqq==0.1.5->-r requirements.txt (line 8)) (2.4.0)\n",
            "Collecting jsonlines (from lm_eval==0.3.0->-r requirements.txt (line 10))\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==0.3.0->-r requirements.txt (line 10)) (2.10.0)\n",
            "Collecting openai>=0.6.4 (from lm_eval==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading openai-1.23.1-py3-none-any.whl (310 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m311.0/311.0 kB\u001b[0m \u001b[31m23.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pybind11>=2.6.2 (from lm_eval==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading pybind11-2.12.0-py3-none-any.whl (234 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m235.0/235.0 kB\u001b[0m \u001b[31m22.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pycountry (from lm_eval==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading pycountry-23.12.11-py3-none-any.whl (6.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.2/6.2 MB\u001b[0m \u001b[31m72.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pytablewriter (from lm_eval==0.3.0->-r requirements.txt (line 10))\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[31m15.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting rouge-score>=0.0.4 (from lm_eval==0.3.0->-r requirements.txt (line 10))\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==0.3.0->-r requirements.txt (line 10))\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[31m10.7 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==0.3.0->-r requirements.txt (line 10)) (1.2.2)\n",
            "Collecting sqlitedict (from lm_eval==0.3.0->-r requirements.txt (line 10))\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==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading tqdm_multiprocess-0.0.11-py3-none-any.whl (9.8 kB)\n",
            "Collecting zstandard (from lm_eval==0.3.0->-r requirements.txt (line 10))\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[31m113.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting llvmlite<0.43,>=0.42.0dev0 (from numba==0.59.*->-r requirements.txt (line 12))\n",
            "  Downloading llvmlite-0.42.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (43.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.8/43.8 MB\u001b[0m \u001b[31m17.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting coloredlogs (from optimum==1.17.*->-r requirements.txt (line 14))\n",
            "  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from optimum==1.17.*->-r requirements.txt (line 14)) (1.12)\n",
            "Requirement already satisfied: transformers[sentencepiece]>=4.26.0 in /usr/local/lib/python3.10/dist-packages (from optimum==1.17.*->-r requirements.txt (line 14)) (4.38.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.39.*->-r requirements.txt (line 26)) (3.13.4)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.39.*->-r requirements.txt (line 26)) (2023.12.25)\n",
            "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers==4.39.*->-r requirements.txt (line 26)) (0.15.2)\n",
            "Requirement already satisfied: Flask>=0.8 in /usr/local/lib/python3.10/dist-packages (from flask_cloudflared==0.0.14->-r requirements.txt (line 32)) (2.2.5)\n",
            "Collecting starlette (from sse-starlette==2.1.0->-r requirements.txt (line 33))\n",
            "  Downloading starlette-0.37.2-py3-none-any.whl (71 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.9/71.9 kB\u001b[0m \u001b[31m10.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from sse-starlette==2.1.0->-r requirements.txt (line 33)) (3.7.1)\n",
            "Collecting autoawq-kernels (from autoawq==0.2.3->-r requirements.txt (line 72))\n",
            "  Downloading autoawq_kernels-0.0.6-cp310-cp310-manylinux2014_x86_64.whl (33.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m33.4/33.4 MB\u001b[0m \u001b[31m22.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.15.1->gradio==4.26.*->-r requirements.txt (line 7)) (2023.6.0)\n",
            "Collecting websockets<12.0,>=10.0 (from gradio-client==0.15.1->gradio==4.26.*->-r requirements.txt (line 7))\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[31m18.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting portalocker (from sacrebleu==1.5.0->lm_eval==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading portalocker-2.8.2-py3-none-any.whl (17 kB)\n",
            "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets->-r requirements.txt (line 5)) (14.0.2)\n",
            "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets->-r requirements.txt (line 5)) (0.6)\n",
            "Collecting dill<0.3.9,>=0.3.0 (from datasets->-r requirements.txt (line 5))\n",
            "  Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m16.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting xxhash (from datasets->-r requirements.txt (line 5))\n",
            "  Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m26.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting multiprocess (from datasets->-r requirements.txt (line 5))\n",
            "  Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m18.9 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 5)) (3.9.5)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 15)) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 15)) (2023.4)\n",
            "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 15)) (2024.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 20)) (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 20)) (3.7)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 20)) (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 20)) (2024.2.2)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich->-r requirements.txt (line 21)) (3.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich->-r requirements.txt (line 21)) (2.16.1)\n",
            "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 25)) (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 25)) (1.62.1)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 25)) (2.27.0)\n",
            "Requirement already satisfied: google-auth-oauthlib<2,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 25)) (1.2.0)\n",
            "Requirement already satisfied: protobuf!=4.24.0,>=3.19.6 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 25)) (3.20.3)\n",
            "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 25)) (67.7.2)\n",
            "Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 25)) (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 25)) (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 25)) (3.0.2)\n",
            "Requirement already satisfied: Click!=8.0.0,>=7.1 in /usr/local/lib/python3.10/dist-packages (from wandb->-r requirements.txt (line 28)) (8.1.7)\n",
            "Collecting GitPython!=3.1.29,>=1.0.0 (from wandb->-r requirements.txt (line 28))\n",
            "  Downloading GitPython-3.1.43-py3-none-any.whl (207 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.3/207.3 kB\u001b[0m \u001b[31m26.3 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 28))\n",
            "  Downloading sentry_sdk-1.45.0-py2.py3-none-any.whl (267 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m267.1/267.1 kB\u001b[0m \u001b[31m28.6 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 28))\n",
            "  Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\n",
            "Collecting setproctitle (from wandb->-r requirements.txt (line 28))\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 28)) (1.4.4)\n",
            "Collecting diskcache>=5.6.1 (from llama-cpp-python==0.2.61+cpuavx2->-r requirements.txt (line 38))\n",
            "  Downloading diskcache-5.6.3-py3-none-any.whl (45 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.5/45.5 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting rouge (from auto-gptq==0.6.0+cu121->-r requirements.txt (line 58))\n",
            "  Downloading rouge-1.0.1-py3-none-any.whl (13 kB)\n",
            "Collecting gekko (from auto-gptq==0.6.0+cu121->-r requirements.txt (line 58))\n",
            "  Downloading gekko-1.1.1-py3-none-any.whl (13.2 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.2/13.2 MB\u001b[0m \u001b[31m98.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting fastparquet (from exllamav2==0.0.18+cu121->-r requirements.txt (line 62))\n",
            "  Downloading fastparquet-2024.2.0-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[31m91.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==4.26.*->-r requirements.txt (line 7)) (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==4.26.*->-r requirements.txt (line 7)) (4.19.2)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==4.26.*->-r requirements.txt (line 7)) (0.12.1)\n",
            "Requirement already satisfied: itsdangerous>=2.0 in /usr/local/lib/python3.10/dist-packages (from Flask>=0.8->flask_cloudflared==0.0.14->-r requirements.txt (line 32)) (2.2.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 5)) (1.3.1)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 5)) (23.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 5)) (1.4.1)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 5)) (6.0.5)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 5)) (1.9.4)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 5)) (4.0.3)\n",
            "Collecting gitdb<5,>=4.0.1 (from GitPython!=3.1.29,>=1.0.0->wandb->-r requirements.txt (line 28))\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 25)) (5.3.3)\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 25)) (0.4.0)\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 25)) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<2,>=0.5->tensorboard->-r requirements.txt (line 25)) (1.3.1)\n",
            "Collecting httpcore==1.* (from httpx>=0.24.1->gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading httpcore-1.0.5-py3-none-any.whl (77 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.9/77.9 kB\u001b[0m \u001b[31m12.1 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>=0.24.1->gradio==4.26.*->-r requirements.txt (line 7)) (1.3.1)\n",
            "Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx>=0.24.1->gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m9.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich->-r requirements.txt (line 21)) (0.1.2)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.*->-r requirements.txt (line 7)) (1.2.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.*->-r requirements.txt (line 7)) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.*->-r requirements.txt (line 7)) (4.51.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.*->-r requirements.txt (line 7)) (1.4.5)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.*->-r requirements.txt (line 7)) (3.1.2)\n",
            "Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai>=0.6.4->lm_eval==0.3.0->-r requirements.txt (line 10)) (1.7.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->sse-starlette==2.1.0->-r requirements.txt (line 33)) (1.2.0)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio==4.26.*->-r requirements.txt (line 7)) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.18.1 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio==4.26.*->-r requirements.txt (line 7)) (2.18.1)\n",
            "Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from rouge-score>=0.0.4->lm_eval==0.3.0->-r requirements.txt (line 10)) (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==0.3.0->-r requirements.txt (line 10)) (1.4.0)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.24.1->lm_eval==0.3.0->-r requirements.txt (line 10)) (3.4.0)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1)) (3.3)\n",
            "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
            "Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
            "Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
            "Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
            "Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
            "Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
            "Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
            "Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
            "Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
            "Collecting nvidia-nccl-cu12==2.19.3 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n",
            "Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
            "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->accelerate==0.27.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n",
            "INFO: pip is looking at multiple versions of transformers[sentencepiece] to determine which version is compatible with other requirements. This could take a while.\n",
            "Collecting transformers[sentencepiece]>=4.26.0 (from optimum==1.17.*->-r requirements.txt (line 14))\n",
            "  Downloading transformers-4.40.0-py3-none-any.whl (9.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.0/9.0 MB\u001b[0m \u001b[31m72.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting shellingham<2.0.0,>=1.3.0 (from typer[all]<1.0,>=0.9->gradio==4.26.*->-r requirements.txt (line 7))\n",
            "  Downloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)\n",
            "Collecting humanfriendly>=9.1 (from coloredlogs->optimum==1.17.*->-r requirements.txt (line 14))\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[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting cramjam>=2.3 (from fastparquet->exllamav2==0.0.18+cu121->-r requirements.txt (line 62))\n",
            "  Downloading cramjam-2.8.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m87.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting DataProperty<2,>=1.0.1 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading DataProperty-1.0.1-py3-none-any.whl (27 kB)\n",
            "Collecting mbstrdecoder<2,>=1.0.0 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading mbstrdecoder-1.1.3-py3-none-any.whl (7.8 kB)\n",
            "Collecting pathvalidate<4,>=2.3.0 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading pathvalidate-3.2.0-py3-none-any.whl (23 kB)\n",
            "Collecting tabledata<2,>=1.3.1 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading tabledata-1.3.3-py3-none-any.whl (11 kB)\n",
            "Collecting tcolorpy<1,>=0.0.5 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 10))\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==0.3.0->-r requirements.txt (line 10))\n",
            "  Downloading typepy-1.3.2-py3-none-any.whl (31 kB)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->optimum==1.17.*->-r requirements.txt (line 14)) (1.3.0)\n",
            "Requirement already satisfied: torchvision in /usr/local/lib/python3.10/dist-packages (from timm->hqq==0.1.5->-r requirements.txt (line 8)) (0.17.1+cu121)\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 28))\n",
            "  Downloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
            "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==4.26.*->-r requirements.txt (line 7)) (2023.12.1)\n",
            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==4.26.*->-r requirements.txt (line 7)) (0.34.0)\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==4.26.*->-r requirements.txt (line 7)) (0.18.0)\n",
            "Requirement already satisfied: chardet<6,>=3.0.4 in /usr/local/lib/python3.10/dist-packages (from mbstrdecoder<2,>=1.0.0->pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 10)) (5.2.0)\n",
            "Requirement already satisfied: pyasn1<0.7.0,>=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 25)) (0.6.0)\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<2,>=0.5->tensorboard->-r requirements.txt (line 25)) (3.2.2)\n",
            "Building wheels for collected packages: hqq, rouge-score, ffmpy, sqlitedict\n",
            "  Building wheel for hqq (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for hqq: filename=hqq-0.1.5-py3-none-any.whl size=42635 sha256=4c6d1330e04f015d7410c9f41799441284bbeae99ab1b314f02997e6595161d2\n",
            "  Stored in directory: /root/.cache/pip/wheels/e1/95/62/11dfb70a0308c6856acf0d712791c2c0492517a63fa3f53bf7\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=f307f10eeb7d9396eb466e64b9f25a838e05916d5861edc034cfc6736c1db254\n",
            "  Stored in directory: /root/.cache/pip/wheels/5f/dd/89/461065a73be61a532ff8599a28e9beef17985c9e9c31e541b4\n",
            "  Building wheel for ffmpy (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for ffmpy: filename=ffmpy-0.3.2-py3-none-any.whl size=5584 sha256=64e051e685bb84a54661ab503f5cee9393083d2f0d99ee8f3dc7c94f94dafed9\n",
            "  Stored in directory: /root/.cache/pip/wheels/bd/65/9a/671fc6dcde07d4418df0c592f8df512b26d7a0029c2a23dd81\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=16862 sha256=de7a7b339405c6c2cc6eefd84690b5c2154c53b04ce4ab2f82a5beb9340027e2\n",
            "  Stored in directory: /root/.cache/pip/wheels/79/d6/e7/304e0e6cb2221022c26d8161f7c23cd4f259a9e41e8bbcfabd\n",
            "Successfully built hqq rouge-score ffmpy sqlitedict\n",
            "Installing collected packages: sqlitedict, pydub, ninja, gptq-for-llama, ffmpy, zstandard, xxhash, websockets, tomlkit, tcolorpy, smmap, shellingham, setproctitle, sentry-sdk, semantic-version, ruff, rouge, python-multipart, pycountry, pybind11, portalocker, Pillow, pathvalidate, orjson, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, numpy, mbstrdecoder, llvmlite, jsonlines, jinja2, humanfriendly, h11, einops, docker-pycreds, diskcache, dill, cramjam, colorama, aiofiles, uvicorn, typepy, tqdm-multiprocess, tiktoken, starlette, SpeechRecognition, sacrebleu, rouge-score, nvidia-cusparse-cu12, nvidia-cudnn-cu12, numba, multiprocess, llama-cpp-python-cuda-tensorcores, llama-cpp-python-cuda, llama-cpp-python, httpcore, gitdb, gekko, coloredlogs, sse-starlette, nvidia-cusolver-cu12, httpx, GitPython, flask_cloudflared, fastparquet, fastapi, wandb, transformers, openai, gradio-client, datasets, DataProperty, tabledata, gradio, flash-attn, exllamav2, bitsandbytes, autoawq-kernels, accelerate, timm, pytablewriter, peft, optimum, autoawq, aqlm, lm_eval, hqq, auto-gptq\n",
            "  Attempting uninstall: Pillow\n",
            "    Found existing installation: Pillow 9.4.0\n",
            "    Uninstalling Pillow-9.4.0:\n",
            "      Successfully uninstalled Pillow-9.4.0\n",
            "  Attempting uninstall: numpy\n",
            "    Found existing installation: numpy 1.25.2\n",
            "    Uninstalling numpy-1.25.2:\n",
            "      Successfully uninstalled numpy-1.25.2\n",
            "  Attempting uninstall: llvmlite\n",
            "    Found existing installation: llvmlite 0.41.1\n",
            "    Uninstalling llvmlite-0.41.1:\n",
            "      Successfully uninstalled llvmlite-0.41.1\n",
            "  Attempting uninstall: jinja2\n",
            "    Found existing installation: Jinja2 3.1.3\n",
            "    Uninstalling Jinja2-3.1.3:\n",
            "      Successfully uninstalled Jinja2-3.1.3\n",
            "  Attempting uninstall: numba\n",
            "    Found existing installation: numba 0.58.1\n",
            "    Uninstalling numba-0.58.1:\n",
            "      Successfully uninstalled numba-0.58.1\n",
            "  Attempting uninstall: transformers\n",
            "    Found existing installation: transformers 4.38.2\n",
            "    Uninstalling transformers-4.38.2:\n",
            "      Successfully uninstalled transformers-4.38.2\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "imageio 2.31.6 requires pillow<10.1.0,>=8.3.2, but you have pillow 10.3.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed DataProperty-1.0.1 GitPython-3.1.43 Pillow-10.3.0 SpeechRecognition-3.10.0 accelerate-0.27.2 aiofiles-23.2.1 aqlm-1.1.3 auto-gptq-0.6.0+cu121 autoawq-0.2.3 autoawq-kernels-0.0.6 bitsandbytes-0.43.1 colorama-0.4.6 coloredlogs-15.0.1 cramjam-2.8.3 datasets-2.18.0 dill-0.3.8 diskcache-5.6.3 docker-pycreds-0.4.0 einops-0.7.0 exllamav2-0.0.18+cu121 fastapi-0.110.2 fastparquet-2024.2.0 ffmpy-0.3.2 flash-attn-2.5.6 flask_cloudflared-0.0.14 gekko-1.1.1 gitdb-4.0.11 gptq-for-llama-0.1.1+cu121 gradio-4.26.0 gradio-client-0.15.1 h11-0.14.0 hqq-0.1.5 httpcore-1.0.5 httpx-0.27.0 humanfriendly-10.0 jinja2-3.1.2 jsonlines-4.0.0 llama-cpp-python-0.2.61+cpuavx2 llama-cpp-python-cuda-0.2.61+cu121 llama-cpp-python-cuda-tensorcores-0.2.61+cu121 llvmlite-0.42.0 lm_eval-0.3.0 mbstrdecoder-1.1.3 multiprocess-0.70.16 ninja-1.11.1.1 numba-0.59.1 numpy-1.26.4 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105 openai-1.23.1 optimum-1.17.1 orjson-3.10.1 pathvalidate-3.2.0 peft-0.8.2 portalocker-2.8.2 pybind11-2.12.0 pycountry-23.12.11 pydub-0.25.1 pytablewriter-1.2.0 python-multipart-0.0.9 rouge-1.0.1 rouge-score-0.1.2 ruff-0.4.0 sacrebleu-1.5.0 semantic-version-2.10.0 sentry-sdk-1.45.0 setproctitle-1.3.3 shellingham-1.5.4 smmap-5.0.1 sqlitedict-2.1.0 sse-starlette-2.1.0 starlette-0.37.2 tabledata-1.3.3 tcolorpy-0.1.4 tiktoken-0.6.0 timm-0.9.16 tomlkit-0.12.0 tqdm-multiprocess-0.0.11 transformers-4.39.3 typepy-1.3.2 uvicorn-0.29.0 wandb-0.16.6 websockets-11.0.3 xxhash-3.4.1 zstandard-0.22.0\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "PIL"
                ]
              },
              "id": "34c24d37e0e3400c90b2a5187bfbda05"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: gradio==4.26.0 in /usr/local/lib/python3.10/dist-packages (4.26.0)\n",
            "Requirement already satisfied: aiofiles<24.0,>=22.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (23.2.1)\n",
            "Requirement already satisfied: altair<6.0,>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (4.2.2)\n",
            "Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.110.2)\n",
            "Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.3.2)\n",
            "Requirement already satisfied: gradio-client==0.15.1 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.15.1)\n",
            "Requirement already satisfied: httpx>=0.24.1 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.27.0)\n",
            "Requirement already satisfied: huggingface-hub>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.20.3)\n",
            "Requirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (6.4.0)\n",
            "Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (3.1.2)\n",
            "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (2.1.5)\n",
            "Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (3.7.1)\n",
            "Requirement already satisfied: numpy~=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (1.26.4)\n",
            "Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (3.10.1)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (24.0)\n",
            "Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (2.0.3)\n",
            "Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (10.3.0)\n",
            "Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (2.7.0)\n",
            "Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.25.1)\n",
            "Requirement already satisfied: python-multipart>=0.0.9 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.0.9)\n",
            "Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (6.0.1)\n",
            "Requirement already satisfied: ruff>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.4.0)\n",
            "Requirement already satisfied: semantic-version~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (2.10.0)\n",
            "Requirement already satisfied: tomlkit==0.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.12.0)\n",
            "Requirement already satisfied: typer[all]<1.0,>=0.9 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.9.4)\n",
            "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (4.11.0)\n",
            "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.29.0)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.15.1->gradio==4.26.0) (2023.6.0)\n",
            "Requirement already satisfied: websockets<12.0,>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.15.1->gradio==4.26.0) (11.0.3)\n",
            "Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==4.26.0) (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==4.26.0) (4.19.2)\n",
            "Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio==4.26.0) (0.12.1)\n",
            "Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio==4.26.0) (3.7.1)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio==4.26.0) (2024.2.2)\n",
            "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio==4.26.0) (1.0.5)\n",
            "Requirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio==4.26.0) (3.7)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio==4.26.0) (1.3.1)\n",
            "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx>=0.24.1->gradio==4.26.0) (0.14.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio==4.26.0) (3.13.4)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio==4.26.0) (2.31.0)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio==4.26.0) (4.66.2)\n",
            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.0) (1.2.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.0) (0.12.1)\n",
            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.0) (4.51.0)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.0) (1.4.5)\n",
            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.0) (3.1.2)\n",
            "Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio==4.26.0) (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==4.26.0) (2023.4)\n",
            "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio==4.26.0) (2024.1)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio==4.26.0) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.18.1 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio==4.26.0) (2.18.1)\n",
            "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.10/dist-packages (from typer[all]<1.0,>=0.9->gradio==4.26.0) (8.1.7)\n",
            "Requirement already satisfied: colorama<0.5.0,>=0.4.3 in /usr/local/lib/python3.10/dist-packages (from typer[all]<1.0,>=0.9->gradio==4.26.0) (0.4.6)\n",
            "Requirement already satisfied: shellingham<2.0.0,>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer[all]<1.0,>=0.9->gradio==4.26.0) (1.5.4)\n",
            "Requirement already satisfied: rich<14.0.0,>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer[all]<1.0,>=0.9->gradio==4.26.0) (13.7.1)\n",
            "Requirement already satisfied: starlette<0.38.0,>=0.37.2 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio==4.26.0) (0.37.2)\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==4.26.0) (23.2.0)\n",
            "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==4.26.0) (2023.12.1)\n",
            "Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==4.26.0) (0.34.0)\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==4.26.0) (0.18.0)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio==4.26.0) (1.16.0)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9->gradio==4.26.0) (3.0.0)\n",
            "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9->gradio==4.26.0) (2.16.1)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx>=0.24.1->gradio==4.26.0) (1.2.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.19.3->gradio==4.26.0) (3.3.2)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.19.3->gradio==4.26.0) (2.0.7)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich<14.0.0,>=10.11.0->typer[all]<1.0,>=0.9->gradio==4.26.0) (0.1.2)\n",
            "Found existing installation: llama_cpp_python 0.2.61+cpuavx2\n",
            "Uninstalling llama_cpp_python-0.2.61+cpuavx2:\n",
            "  Successfully uninstalled llama_cpp_python-0.2.61+cpuavx2\n",
            "Collecting llama-cpp-python\n",
            "  Downloading llama_cpp_python-0.2.62.tar.gz (37.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m37.5/37.5 MB\u001b[0m \u001b[31m166.7 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) (4.11.0)\n",
            "Requirement already satisfied: numpy>=1.20.0 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python) (1.26.4)\n",
            "Requirement already satisfied: diskcache>=5.6.1 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python) (5.6.3)\n",
            "Requirement already satisfied: jinja2>=2.11.3 in /usr/local/lib/python3.10/dist-packages (from llama-cpp-python) (3.1.2)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2>=2.11.3->llama-cpp-python) (2.1.5)\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-0.2.62-cp310-cp310-manylinux_2_35_x86_64.whl size=39013319 sha256=0d4af61a2ca7d1d5e4d1f4e088fc51e009a0c5e53dce9d71bd4318d01d388bbc\n",
            "  Stored in directory: /tmp/pip-ephem-wheel-cache-7w3f0a5r/wheels/c0/81/de/d4cc8f152d89865379dbf28ca672358c667192ee55deaca7cb\n",
            "Successfully built llama-cpp-python\n",
            "Installing collected packages: llama-cpp-python\n",
            "Successfully installed llama-cpp-python-0.2.62\n",
            "Found existing installation: flash-attn 2.5.6\n",
            "Uninstalling flash-attn-2.5.6:\n",
            "  Successfully uninstalled flash-attn-2.5.6\n",
            "Collecting flash-attn==2.5.6\n",
            "  Downloading flash_attn-2.5.6.tar.gz (2.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.5/2.5 MB\u001b[0m \u001b[31m16.1 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==2.5.6) (2.2.1+cu121)\n",
            "Requirement already satisfied: einops in /usr/local/lib/python3.10/dist-packages (from flash-attn==2.5.6) (0.7.0)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from flash-attn==2.5.6) (24.0)\n",
            "Requirement already satisfied: ninja in /usr/local/lib/python3.10/dist-packages (from flash-attn==2.5.6) (1.11.1.1)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (3.13.4)\n",
            "Requirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (4.11.0)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (1.12)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (3.3)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (3.1.2)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (2023.6.0)\n",
            "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (12.1.105)\n",
            "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (12.1.105)\n",
            "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (12.1.105)\n",
            "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (8.9.2.26)\n",
            "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (12.1.3.1)\n",
            "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (11.0.2.54)\n",
            "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (10.3.2.106)\n",
            "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (11.4.5.107)\n",
            "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (12.1.0.106)\n",
            "Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (2.19.3)\n",
            "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (12.1.105)\n",
            "Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch->flash-attn==2.5.6) (2.2.0)\n",
            "Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch->flash-attn==2.5.6) (12.4.127)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->flash-attn==2.5.6) (2.1.5)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->flash-attn==2.5.6) (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-2.5.6-cp310-cp310-linux_x86_64.whl size=120592258 sha256=d8cf54adda65f59820221d329d274e124972d7fdc05ab3b1130253c64eee6c8a\n",
            "  Stored in directory: /root/.cache/pip/wheels/a8/1c/88/b959d6818b98a46d61ba231683abb7523b89ac1a7ed1e0c206\n",
            "Successfully built flash-attn\n",
            "Installing collected packages: flash-attn\n",
            "Successfully installed flash-attn-2.5.6\n",
            "\u001b[0m\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "c21a28|\u001b[1;32mOK\u001b[0m  |   197MiB/s|/content/text-generation-webui/models//Meta-Llama-3-8B-Instruct.Q5_K_M.gguf\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "/content/text-generation-webui\n",
            "\u001b[2;36m02:49:22-092201\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Starting Text generation web UI                                            \n",
            "\u001b[2;36m02:49:22-745038\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Loading \u001b[32m\"Meta-Llama-3-8B-Instruct.Q5_K_M.gguf\"\u001b[0m                             \n",
            "\u001b[2;36m02:49:23-312826\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m llama.cpp weights detected: \u001b[32m\"models/Meta-Llama-3-8B-Instruct.Q5_K_M.gguf\"\u001b[0m  \n",
            "llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from models/Meta-Llama-3-8B-Instruct.Q5_K_M.gguf (version GGUF V3 (latest))\n",
            "llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.\n",
            "llama_model_loader: - kv   0:                       general.architecture str              = llama\n",
            "llama_model_loader: - kv   1:                               general.name str              = .\n",
            "llama_model_loader: - kv   2:                           llama.vocab_size u32              = 128256\n",
            "llama_model_loader: - kv   3:                       llama.context_length u32              = 8192\n",
            "llama_model_loader: - kv   4:                     llama.embedding_length u32              = 4096\n",
            "llama_model_loader: - kv   5:                          llama.block_count u32              = 32\n",
            "llama_model_loader: - kv   6:                  llama.feed_forward_length u32              = 14336\n",
            "llama_model_loader: - kv   7:                 llama.rope.dimension_count u32              = 128\n",
            "llama_model_loader: - kv   8:                 llama.attention.head_count u32              = 32\n",
            "llama_model_loader: - kv   9:              llama.attention.head_count_kv u32              = 8\n",
            "llama_model_loader: - kv  10:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010\n",
            "llama_model_loader: - kv  11:                       llama.rope.freq_base f32              = 500000.000000\n",
            "llama_model_loader: - kv  12:                          general.file_type u32              = 17\n",
            "llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2\n",
            "llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,128256]  = [\"!\", \"\\\"\", \"#\", \"$\", \"%\", \"&\", \"'\", ...\n",
            "llama_model_loader: - kv  15:                      tokenizer.ggml.scores arr[f32,128256]  = [0.000000, 0.000000, 0.000000, 0.0000...\n",
            "llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...\n",
            "llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,280147]  = [\"Ġ Ġ\", \"Ġ ĠĠĠ\", \"ĠĠ ĠĠ\", \"...\n",
            "llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 128000\n",
            "llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 128009\n",
            "llama_model_loader: - kv  20:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...\n",
            "llama_model_loader: - kv  21:               general.quantization_version u32              = 2\n",
            "llama_model_loader: - type  f32:   65 tensors\n",
            "llama_model_loader: - type q5_K:  193 tensors\n",
            "llama_model_loader: - type q6_K:   33 tensors\n",
            "llm_load_vocab: special tokens definition check successful ( 256/128256 ).\n",
            "llm_load_print_meta: format           = GGUF V3 (latest)\n",
            "llm_load_print_meta: arch             = llama\n",
            "llm_load_print_meta: vocab type       = BPE\n",
            "llm_load_print_meta: n_vocab          = 128256\n",
            "llm_load_print_meta: n_merges         = 280147\n",
            "llm_load_print_meta: n_ctx_train      = 8192\n",
            "llm_load_print_meta: n_embd           = 4096\n",
            "llm_load_print_meta: n_head           = 32\n",
            "llm_load_print_meta: n_head_kv        = 8\n",
            "llm_load_print_meta: n_layer          = 32\n",
            "llm_load_print_meta: n_rot            = 128\n",
            "llm_load_print_meta: n_embd_head_k    = 128\n",
            "llm_load_print_meta: n_embd_head_v    = 128\n",
            "llm_load_print_meta: n_gqa            = 4\n",
            "llm_load_print_meta: n_embd_k_gqa     = 1024\n",
            "llm_load_print_meta: n_embd_v_gqa     = 1024\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: f_logit_scale    = 0.0e+00\n",
            "llm_load_print_meta: n_ff             = 14336\n",
            "llm_load_print_meta: n_expert         = 0\n",
            "llm_load_print_meta: n_expert_used    = 0\n",
            "llm_load_print_meta: causal attn      = 1\n",
            "llm_load_print_meta: pooling type     = 0\n",
            "llm_load_print_meta: rope type        = 0\n",
            "llm_load_print_meta: rope scaling     = linear\n",
            "llm_load_print_meta: freq_base_train  = 500000.0\n",
            "llm_load_print_meta: freq_scale_train = 1\n",
            "llm_load_print_meta: n_yarn_orig_ctx  = 8192\n",
            "llm_load_print_meta: rope_finetuned   = unknown\n",
            "llm_load_print_meta: ssm_d_conv       = 0\n",
            "llm_load_print_meta: ssm_d_inner      = 0\n",
            "llm_load_print_meta: ssm_d_state      = 0\n",
            "llm_load_print_meta: ssm_dt_rank      = 0\n",
            "llm_load_print_meta: model type       = 7B\n",
            "llm_load_print_meta: model ftype      = Q5_K - Medium\n",
            "llm_load_print_meta: model params     = 8.03 B\n",
            "llm_load_print_meta: model size       = 5.33 GiB (5.70 BPW) \n",
            "llm_load_print_meta: general.name     = .\n",
            "llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'\n",
            "llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'\n",
            "llm_load_print_meta: LF token         = 128 'Ä'\n",
            "ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   yes\n",
            "ggml_cuda_init: CUDA_USE_TENSOR_CORES: no\n",
            "ggml_cuda_init: found 1 CUDA devices:\n",
            "  Device 0: Tesla T4, compute capability 7.5, VMM: yes\n",
            "llm_load_tensors: ggml ctx size =    0.22 MiB\n",
            "llm_load_tensors: offloading 32 repeating layers to GPU\n",
            "llm_load_tensors: offloading non-repeating layers to GPU\n",
            "llm_load_tensors: offloaded 33/33 layers to GPU\n",
            "llm_load_tensors:        CPU buffer size =   344.44 MiB\n",
            "llm_load_tensors:      CUDA0 buffer size =  5115.49 MiB\n",
            ".........................................................................................\n",
            "llama_new_context_with_model: n_ctx      = 8192\n",
            "llama_new_context_with_model: n_batch    = 512\n",
            "llama_new_context_with_model: n_ubatch   = 512\n",
            "llama_new_context_with_model: freq_base  = 500000.0\n",
            "llama_new_context_with_model: freq_scale = 1\n",
            "llama_kv_cache_init:      CUDA0 KV buffer size =  1024.00 MiB\n",
            "llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB\n",
            "llama_new_context_with_model:  CUDA_Host  output buffer size =     0.49 MiB\n",
            "llama_new_context_with_model:      CUDA0 compute buffer size =   560.00 MiB\n",
            "llama_new_context_with_model:  CUDA_Host compute buffer size =    24.01 MiB\n",
            "llama_new_context_with_model: graph nodes  = 1030\n",
            "llama_new_context_with_model: graph splits = 2\n",
            "AVX = 1 | AVX_VNNI = 0 | 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 | MATMUL_INT8 = 0 | \n",
            "Model metadata: {'tokenizer.chat_template': \"{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\", 'tokenizer.ggml.eos_token_id': '128009', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'gpt2', 'general.architecture': 'llama', 'llama.rope.freq_base': '500000.000000', 'llama.context_length': '8192', 'general.name': '.', 'llama.vocab_size': '128256', 'general.file_type': '17', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '14336', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'llama.rope.dimension_count': '128', 'tokenizer.ggml.bos_token_id': '128000', 'llama.attention.head_count': '32', 'llama.block_count': '32', 'llama.attention.head_count_kv': '8'}\n",
            "Using gguf chat template: {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n",
            "\n",
            "'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n",
            "\n",
            "' }}\n",
            "Using chat eos_token: <|eot_id|>\n",
            "Using chat bos_token: <|begin_of_text|>\n",
            "\u001b[2;36m02:49:43-560807\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m LOADER: \u001b[32m\"llama.cpp\"\u001b[0m                                                        \n",
            "\u001b[2;36m02:49:43-564505\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m TRUNCATION LENGTH: \u001b[1;36m8192\u001b[0m                                                    \n",
            "\u001b[2;36m02:49:43-566247\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m INSTRUCTION TEMPLATE: \u001b[32m\"Custom \u001b[0m\u001b[32m(\u001b[0m\u001b[32mobtained from model metadata\u001b[0m\u001b[32m)\u001b[0m\u001b[32m\"\u001b[0m              \n",
            "\u001b[2;36m02:49:43-568068\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Loaded the model in \u001b[1;36m20.82\u001b[0m seconds.                                         \n",
            "\n",
            "Running on local URL:  http://127.0.0.1:7860\n",
            "\n",
            "Running on public URL: https://3c1f021534019681b2.gradio.live\n",
            "\n",
            "This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n",
            "\n",
            "llama_print_timings:        load time =     604.40 ms\n",
            "llama_print_timings:      sample time =     787.05 ms /    92 runs   (    8.55 ms per token,   116.89 tokens per second)\n",
            "llama_print_timings: prompt eval time =     601.66 ms /    27 tokens (   22.28 ms per token,    44.88 tokens per second)\n",
            "llama_print_timings:        eval time =    2390.87 ms /    91 runs   (   26.27 ms per token,    38.06 tokens per second)\n",
            "llama_print_timings:       total time =    4969.42 ms /   118 tokens\n",
            "Output generated in 5.69 seconds (16.51 tokens/s, 94 tokens, context 60, seed 436402402)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =     604.40 ms\n",
            "llama_print_timings:      sample time =     202.92 ms /    24 runs   (    8.46 ms per token,   118.27 tokens per second)\n",
            "llama_print_timings: prompt eval time =     410.76 ms /   125 tokens (    3.29 ms per token,   304.31 tokens per second)\n",
            "llama_print_timings:        eval time =     608.89 ms /    23 runs   (   26.47 ms per token,    37.77 tokens per second)\n",
            "llama_print_timings:       total time =    1514.04 ms /   148 tokens\n",
            "Output generated in 2.10 seconds (11.42 tokens/s, 24 tokens, context 217, seed 1374374780)\n",
            "Llama.generate: prefix-match hit\n",
            "\n",
            "llama_print_timings:        load time =     604.40 ms\n",
            "llama_print_timings:      sample time =     170.88 ms /    20 runs   (    8.54 ms per token,   117.04 tokens per second)\n",
            "llama_print_timings: prompt eval time =     296.90 ms /    52 tokens (    5.71 ms per token,   175.14 tokens per second)\n",
            "llama_print_timings:        eval time =     506.39 ms /    19 runs   (   26.65 ms per token,    37.52 tokens per second)\n",
            "llama_print_timings:       total time =    1212.44 ms /    71 tokens\n",
            "Output generated in 1.86 seconds (10.75 tokens/s, 20 tokens, context 300, seed 198185173)\n",
            "\u001b[2;36m02:51:58-348817\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Deleted \u001b[32m\"logs/instruct/20240419-02-50-17.json\"\u001b[0m.                            \n"
          ]
        }
      ],
      "source": [
        "%cd /content\n",
        "!apt-get -y install -qq aria2\n",
        "\n",
        "!git clone -b V20240418 https://github.com/Troyanovsky/text-generation-webui\n",
        "%cd /content/text-generation-webui\n",
        "!pip install -r requirements.txt\n",
        "!pip install -U gradio==4.26.0\n",
        "\n",
        "!pip uninstall -y llama-cpp-python -y\n",
        "!CMAKE_ARGS=\"-DLLAMA_CUDA=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==2.5.6\n",
        "\n",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/QuantFactory/Meta-Llama-3-8B-Instruct-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.Q5_K_M.gguf?download=true -d /content/text-generation-webui/models/ -o Meta-Llama-3-8B-Instruct.Q5_K_M.gguf\n",
        "\n",
        "%cd /content/text-generation-webui\n",
        "!python server.py --share --n-gpu-layers 100000 --model Meta-Llama-3-8B-Instruct.Q5_K_M.gguf"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMo91jQYTzyyYucQ9K8UOSw",
      "include_colab_link": true
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}