Mistral_NeMo_Minitron_8B_Base_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/Mistral_NeMo_Minitron_8B_Base_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": [
        "## Mistral-NeMo-Minitron-8B-Base-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: None\n",
        "(Base models don't have instruction templates but you can try Mistral Instruct)\n",
        "\n",
        "Original model: https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base\n",
        "\n",
        "Quantized model: https://huggingface.co/QuantFactory/Mistral-NeMo-Minitron-8B-Base-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": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "D-MiHp_bveP6",
        "outputId": "7aac171c-9f95-456b-a478-d7aaf224c8a1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content\n",
            "Selecting previously unselected package libc-ares2:amd64.\n",
            "(Reading database ... 123595 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/libtbbmalloc_proxy.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbb.so.12 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbmalloc.so.2 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libur_adapter_opencl.so.0 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/libur_adapter_level_zero.so.0 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libur_loader.so.0 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_5.so.3 is not a symbolic link\n",
            "\n",
            "/sbin/ldconfig.real: /usr/local/lib/libtbbbind_2_0.so.3 is not a symbolic link\n",
            "\n",
            "Cloning into 'text-generation-webui'...\n",
            "remote: Enumerating objects: 18825, done.\u001b[K\n",
            "remote: Counting objects: 100% (459/459), done.\u001b[K\n",
            "remote: Compressing objects: 100% (212/212), done.\u001b[K\n",
            "remote: Total 18825 (delta 320), reused 331 (delta 247), pack-reused 18366 (from 1)\u001b[K\n",
            "Receiving objects: 100% (18825/18825), 27.83 MiB | 16.83 MiB/s, done.\n",
            "Resolving deltas: 100% (13328/13328), done.\n",
            "Note: switching to 'd011040f43c447d699dfd4cf863198907e16c10d'.\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==0.2.85+cpuavx2 (from -r requirements.txt (line 39))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.85+cpuavx2-cp310-cp310-linux_x86_64.whl (2.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.8/2.8 MB\u001b[0m \u001b[31m47.7 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==0.2.85+cu121 (from -r requirements.txt (line 47))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.85+cu121-cp310-cp310-linux_x86_64.whl (397.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m397.5/397.5 MB\u001b[0m \u001b[31m3.7 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==0.2.85+cu121 (from -r requirements.txt (line 53))\n",
            "  Downloading https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.85+cu121-cp310-cp310-linux_x86_64.whl (434.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m434.1/434.1 MB\u001b[0m \u001b[31m4.0 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==0.1.8+cu121.torch2.2.2 (from -r requirements.txt (line 59))\n",
            "  Downloading https://github.com/oobabooga/exllamav2/releases/download/v0.1.8/exllamav2-0.1.8+cu121.torch2.2.2-cp310-cp310-linux_x86_64.whl (135.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m135.6/135.6 MB\u001b[0m \u001b[31m7.0 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==2.6.1+cu123torch2.2cxx11abiFALSE (from -r requirements.txt (line 64))\n",
            "  Downloading https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.1/flash_attn-2.6.1+cu123torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl (198.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m198.4/198.4 MB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring autoawq: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring autoawq: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring autoawq: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting autoawq==0.2.6 (from -r requirements.txt (line 68))\n",
            "  Downloading https://github.com/oobabooga/AutoAWQ/releases/download/0.2.6/autoawq-0.2.6-cp310-cp310-linux_x86_64.whl (94 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.9/94.9 kB\u001b[0m \u001b[31m8.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hIgnoring autoawq-kernels: markers 'platform_system == \"Windows\" and python_version == \"3.11\"' don't match your environment\n",
            "Ignoring autoawq-kernels: markers 'platform_system == \"Windows\" and python_version == \"3.10\"' don't match your environment\n",
            "Ignoring autoawq-kernels: markers 'platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version == \"3.11\"' don't match your environment\n",
            "Collecting autoawq-kernels==0.0.7 (from -r requirements.txt (line 72))\n",
            "  Downloading https://github.com/oobabooga/AutoAWQ_kernels/releases/download/0.0.7/autoawq_kernels-0.0.7-cp310-cp310-linux_x86_64.whl (33.4 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m33.4/33.4 MB\u001b[0m \u001b[31m57.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: accelerate==0.32.* in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 1)) (0.32.1)\n",
            "Collecting aqlm==1.1.6 (from aqlm[cpu,gpu]==1.1.6->-r requirements.txt (line 2))\n",
            "  Downloading aqlm-1.1.6-py3-none-any.whl.metadata (1.7 kB)\n",
            "Collecting auto-gptq==0.7.1 (from -r requirements.txt (line 3))\n",
            "  Downloading auto_gptq-0.7.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (18 kB)\n",
            "Collecting bitsandbytes==0.43.* (from -r requirements.txt (line 4))\n",
            "  Downloading bitsandbytes-0.43.3-py3-none-manylinux_2_24_x86_64.whl.metadata (3.5 kB)\n",
            "Collecting colorama (from -r requirements.txt (line 5))\n",
            "  Downloading colorama-0.4.6-py2.py3-none-any.whl.metadata (17 kB)\n",
            "Collecting datasets (from -r requirements.txt (line 6))\n",
            "  Downloading datasets-2.21.0-py3-none-any.whl.metadata (21 kB)\n",
            "Requirement already satisfied: einops in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 7)) (0.8.0)\n",
            "Collecting gradio==4.26.* (from -r requirements.txt (line 8))\n",
            "  Downloading gradio-4.26.0-py3-none-any.whl.metadata (15 kB)\n",
            "Collecting hqq==0.1.7.post3 (from -r requirements.txt (line 9))\n",
            "  Downloading hqq-0.1.7.post3.tar.gz (50 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.3/50.3 kB\u001b[0m \u001b[31m5.1 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: jinja2==3.1.4 in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 10)) (3.1.4)\n",
            "Collecting lm_eval==0.3.0 (from -r requirements.txt (line 11))\n",
            "  Downloading lm_eval-0.3.0-py3-none-any.whl.metadata (6.8 kB)\n",
            "Requirement already satisfied: markdown in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 12)) (3.7)\n",
            "Collecting numba==0.59.* (from -r requirements.txt (line 13))\n",
            "  Downloading numba-0.59.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (2.7 kB)\n",
            "Requirement already satisfied: numpy==1.26.* in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 14)) (1.26.4)\n",
            "Collecting optimum==1.17.* (from -r requirements.txt (line 15))\n",
            "  Downloading optimum-1.17.1-py3-none-any.whl.metadata (18 kB)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 16)) (2.1.4)\n",
            "Collecting peft==0.8.* (from -r requirements.txt (line 17))\n",
            "  Downloading peft-0.8.2-py3-none-any.whl.metadata (25 kB)\n",
            "Collecting Pillow>=9.5.0 (from -r requirements.txt (line 18))\n",
            "  Downloading pillow-10.4.0-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (9.2 kB)\n",
            "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 19)) (5.9.5)\n",
            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 20)) (6.0.2)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 21)) (2.32.3)\n",
            "Requirement already satisfied: rich in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 22)) (13.7.1)\n",
            "Requirement already satisfied: safetensors==0.4.* in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 23)) (0.4.4)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 24)) (1.13.1)\n",
            "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 25)) (0.1.99)\n",
            "Requirement already satisfied: tensorboard in /usr/local/lib/python3.10/dist-packages (from -r requirements.txt (line 26)) (2.17.0)\n",
            "Collecting transformers==4.43.* (from -r requirements.txt (line 27))\n",
            "  Downloading transformers-4.43.4-py3-none-any.whl.metadata (43 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.7/43.7 kB\u001b[0m \u001b[31m3.9 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 28)) (4.66.5)\n",
            "Collecting wandb (from -r requirements.txt (line 29))\n",
            "  Downloading wandb-0.17.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (10 kB)\n",
            "Collecting SpeechRecognition==3.10.0 (from -r requirements.txt (line 32))\n",
            "  Downloading SpeechRecognition-3.10.0-py2.py3-none-any.whl.metadata (28 kB)\n",
            "Collecting flask_cloudflared==0.0.14 (from -r requirements.txt (line 33))\n",
            "  Downloading flask_cloudflared-0.0.14-py3-none-any.whl.metadata (4.6 kB)\n",
            "Collecting sse-starlette==1.6.5 (from -r requirements.txt (line 34))\n",
            "  Downloading sse_starlette-1.6.5-py3-none-any.whl.metadata (6.7 kB)\n",
            "Collecting tiktoken (from -r requirements.txt (line 35))\n",
            "  Downloading tiktoken-0.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.6 kB)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.32.*->-r requirements.txt (line 1)) (24.1)\n",
            "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate==0.32.*->-r requirements.txt (line 1)) (2.3.1+cu121)\n",
            "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate==0.32.*->-r requirements.txt (line 1)) (0.23.5)\n",
            "Collecting rouge (from auto-gptq==0.7.1->-r requirements.txt (line 3))\n",
            "  Downloading rouge-1.0.1-py3-none-any.whl.metadata (4.1 kB)\n",
            "Collecting gekko (from auto-gptq==0.7.1->-r requirements.txt (line 3))\n",
            "  Downloading gekko-1.2.1-py3-none-any.whl.metadata (3.0 kB)\n",
            "Collecting aiofiles<24.0,>=22.0 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 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 8)) (4.2.2)\n",
            "Collecting fastapi (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading fastapi-0.112.2-py3-none-any.whl.metadata (27 kB)\n",
            "Collecting ffmpy (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading ffmpy-0.4.0-py3-none-any.whl.metadata (2.9 kB)\n",
            "Collecting gradio-client==0.15.1 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading gradio_client-0.15.1-py3-none-any.whl.metadata (7.1 kB)\n",
            "Collecting httpx>=0.24.1 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading httpx-0.27.0-py3-none-any.whl.metadata (7.2 kB)\n",
            "Requirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 8)) (6.4.3)\n",
            "Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 8)) (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 8)) (3.7.1)\n",
            "Collecting orjson~=3.0 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading orjson-3.10.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (50 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.4/50.4 kB\u001b[0m \u001b[31m4.1 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 8)) (2.8.2)\n",
            "Collecting pydub (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
            "Collecting python-multipart>=0.0.9 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading python_multipart-0.0.9-py3-none-any.whl.metadata (2.5 kB)\n",
            "Collecting ruff>=0.2.2 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading ruff-0.6.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (25 kB)\n",
            "Collecting semantic-version~=2.0 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n",
            "Collecting tomlkit==0.12.0 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading tomlkit-0.12.0-py3-none-any.whl.metadata (2.7 kB)\n",
            "Requirement already satisfied: typer<1.0,>=0.9 in /usr/local/lib/python3.10/dist-packages (from typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio==4.26.*->-r requirements.txt (line 8)) (0.12.4)\n",
            "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.*->-r requirements.txt (line 8)) (4.12.2)\n",
            "Collecting uvicorn>=0.14.0 (from gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading uvicorn-0.30.6-py3-none-any.whl.metadata (6.6 kB)\n",
            "Requirement already satisfied: termcolor in /usr/local/lib/python3.10/dist-packages (from hqq==0.1.7.post3->-r requirements.txt (line 9)) (2.4.0)\n",
            "Collecting jsonlines (from lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading jsonlines-4.0.0-py3-none-any.whl.metadata (1.6 kB)\n",
            "Requirement already satisfied: numexpr in /usr/local/lib/python3.10/dist-packages (from lm_eval==0.3.0->-r requirements.txt (line 11)) (2.10.1)\n",
            "Collecting openai>=0.6.4 (from lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading openai-1.42.0-py3-none-any.whl.metadata (22 kB)\n",
            "Collecting pybind11>=2.6.2 (from lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading pybind11-2.13.5-py3-none-any.whl.metadata (9.5 kB)\n",
            "Collecting pycountry (from lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading pycountry-24.6.1-py3-none-any.whl.metadata (12 kB)\n",
            "Collecting pytablewriter (from lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading pytablewriter-1.2.0-py3-none-any.whl.metadata (37 kB)\n",
            "Collecting rouge-score>=0.0.4 (from lm_eval==0.3.0->-r requirements.txt (line 11))\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 11))\n",
            "  Downloading sacrebleu-1.5.0-py3-none-any.whl.metadata (1.3 kB)\n",
            "Requirement 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 11)) (1.3.2)\n",
            "Collecting sqlitedict (from lm_eval==0.3.0->-r requirements.txt (line 11))\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 11))\n",
            "  Downloading tqdm_multiprocess-0.0.11-py3-none-any.whl.metadata (5.7 kB)\n",
            "Collecting zstandard (from lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading zstandard-0.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.0 kB)\n",
            "Collecting llvmlite<0.43,>=0.42.0dev0 (from numba==0.59.*->-r requirements.txt (line 13))\n",
            "  Downloading llvmlite-0.42.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.8 kB)\n",
            "Collecting coloredlogs (from optimum==1.17.*->-r requirements.txt (line 15))\n",
            "  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl.metadata (12 kB)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from optimum==1.17.*->-r requirements.txt (line 15)) (1.13.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.*->-r requirements.txt (line 27)) (3.15.4)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.*->-r requirements.txt (line 27)) (2024.5.15)\n",
            "Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers==4.43.*->-r requirements.txt (line 27)) (0.19.1)\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 33)) (2.2.5)\n",
            "Collecting starlette (from sse-starlette==1.6.5->-r requirements.txt (line 34))\n",
            "  Downloading starlette-0.38.2-py3-none-any.whl.metadata (5.9 kB)\n",
            "Requirement already satisfied: triton>=2.1 in /usr/local/lib/python3.10/dist-packages (from aqlm[cpu,gpu]==1.1.6->-r requirements.txt (line 2)) (2.3.1)\n",
            "Collecting ninja (from aqlm[cpu,gpu]==1.1.6->-r requirements.txt (line 2))\n",
            "  Downloading ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl.metadata (5.3 kB)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.15.1->gradio==4.26.*->-r requirements.txt (line 8)) (2024.6.1)\n",
            "Collecting websockets<12.0,>=10.0 (from gradio-client==0.15.1->gradio==4.26.*->-r requirements.txt (line 8))\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.metadata (6.6 kB)\n",
            "Collecting portalocker (from sacrebleu==1.5.0->lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading portalocker-2.10.1-py3-none-any.whl.metadata (8.5 kB)\n",
            "Collecting pyarrow>=15.0.0 (from datasets->-r requirements.txt (line 6))\n",
            "  Downloading pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.3 kB)\n",
            "Collecting dill<0.3.9,>=0.3.0 (from datasets->-r requirements.txt (line 6))\n",
            "  Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n",
            "Collecting xxhash (from datasets->-r requirements.txt (line 6))\n",
            "  Downloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
            "Collecting multiprocess (from datasets->-r requirements.txt (line 6))\n",
            "  Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets->-r requirements.txt (line 6)) (3.10.5)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 16)) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 16)) (2024.1)\n",
            "Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->-r requirements.txt (line 16)) (2024.1)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->-r requirements.txt (line 21)) (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 21)) (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 21)) (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 21)) (2024.7.4)\n",
            "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich->-r requirements.txt (line 22)) (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 22)) (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 26)) (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 26)) (1.64.1)\n",
            "Requirement already satisfied: protobuf!=4.24.0,<5.0.0,>=3.19.6 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 26)) (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 26)) (71.0.4)\n",
            "Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/dist-packages (from tensorboard->-r requirements.txt (line 26)) (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 26)) (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 26)) (3.0.3)\n",
            "Requirement already satisfied: click!=8.0.0,>=7.1 in /usr/local/lib/python3.10/dist-packages (from wandb->-r requirements.txt (line 29)) (8.1.7)\n",
            "Collecting docker-pycreds>=0.4.0 (from wandb->-r requirements.txt (line 29))\n",
            "  Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl.metadata (1.8 kB)\n",
            "Collecting gitpython!=3.1.29,>=1.0.0 (from wandb->-r requirements.txt (line 29))\n",
            "  Downloading GitPython-3.1.43-py3-none-any.whl.metadata (13 kB)\n",
            "Requirement already satisfied: platformdirs in /usr/local/lib/python3.10/dist-packages (from wandb->-r requirements.txt (line 29)) (4.2.2)\n",
            "Collecting sentry-sdk>=1.0.0 (from wandb->-r requirements.txt (line 29))\n",
            "  Downloading sentry_sdk-2.13.0-py2.py3-none-any.whl.metadata (9.7 kB)\n",
            "Collecting setproctitle (from wandb->-r requirements.txt (line 29))\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.metadata (9.9 kB)\n",
            "Collecting diskcache>=5.6.1 (from llama-cpp-python==0.2.85+cpuavx2->-r requirements.txt (line 39))\n",
            "  Downloading diskcache-5.6.3-py3-none-any.whl.metadata (20 kB)\n",
            "Collecting fastparquet (from exllamav2==0.1.8+cu121.torch2.2.2->-r requirements.txt (line 59))\n",
            "  Downloading fastparquet-2024.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.1 kB)\n",
            "Collecting torch>=1.10.0 (from accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Downloading torch-2.2.2-cp310-cp310-manylinux1_x86_64.whl.metadata (26 kB)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1)) (3.3)\n",
            "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
            "Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl.metadata (1.6 kB)\n",
            "Collecting nvidia-nccl-cu12==2.19.3 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Downloading nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl.metadata (1.8 kB)\n",
            "Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.7 kB)\n",
            "Collecting triton>=2.1 (from aqlm[cpu,gpu]==1.1.6->-r requirements.txt (line 2))\n",
            "  Downloading triton-2.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.4 kB)\n",
            "Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->accelerate==0.32.*->-r requirements.txt (line 1))\n",
            "  Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
            "Requirement 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 8)) (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 8)) (4.23.0)\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 8)) (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 33)) (2.2.0)\n",
            "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 6)) (2.4.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 6)) (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 6)) (24.2.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->-r requirements.txt (line 6)) (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 6)) (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 6)) (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 6)) (4.0.3)\n",
            "Collecting gitdb<5,>=4.0.1 (from gitpython!=3.1.29,>=1.0.0->wandb->-r requirements.txt (line 29))\n",
            "  Downloading gitdb-4.0.11-py3-none-any.whl.metadata (1.2 kB)\n",
            "Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio==4.26.*->-r requirements.txt (line 8)) (3.7.1)\n",
            "Collecting httpcore==1.* (from httpx>=0.24.1->gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading httpcore-1.0.5-py3-none-any.whl.metadata (20 kB)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio==4.26.*->-r requirements.txt (line 8)) (1.3.1)\n",
            "Collecting h11<0.15,>=0.13 (from httpcore==1.*->httpx>=0.24.1->gradio==4.26.*->-r requirements.txt (line 8))\n",
            "  Downloading h11-0.14.0-py3-none-any.whl.metadata (8.2 kB)\n",
            "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich->-r requirements.txt (line 22)) (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 8)) (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 8)) (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 8)) (4.53.1)\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 8)) (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 8)) (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 11)) (1.7.0)\n",
            "Collecting jiter<1,>=0.4.0 (from openai>=0.6.4->lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading jiter-0.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.6 kB)\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 8)) (0.7.0)\n",
            "Requirement already satisfied: pydantic-core==2.20.1 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio==4.26.*->-r requirements.txt (line 8)) (2.20.1)\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 11)) (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 11)) (1.4.2)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.24.1->lm_eval==0.3.0->-r requirements.txt (line 11)) (3.5.0)\n",
            "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.9->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio==4.26.*->-r requirements.txt (line 8)) (1.5.4)\n",
            "\u001b[33mWARNING: typer 0.12.4 does not provide the extra 'all'\u001b[0m\u001b[33m\n",
            "\u001b[0mCollecting humanfriendly>=9.1 (from coloredlogs->optimum==1.17.*->-r requirements.txt (line 15))\n",
            "  Downloading humanfriendly-10.0-py2.py3-none-any.whl.metadata (9.2 kB)\n",
            "Collecting cramjam>=2.3 (from fastparquet->exllamav2==0.1.8+cu121.torch2.2.2->-r requirements.txt (line 59))\n",
            "  Downloading cramjam-2.8.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.2 kB)\n",
            "Collecting DataProperty<2,>=1.0.1 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading DataProperty-1.0.1-py3-none-any.whl.metadata (11 kB)\n",
            "Collecting mbstrdecoder<2,>=1.0.0 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading mbstrdecoder-1.1.3-py3-none-any.whl.metadata (4.0 kB)\n",
            "Collecting pathvalidate<4,>=2.3.0 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading pathvalidate-3.2.1-py3-none-any.whl.metadata (12 kB)\n",
            "Collecting tabledata<2,>=1.3.1 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading tabledata-1.3.3-py3-none-any.whl.metadata (3.7 kB)\n",
            "Collecting tcolorpy<1,>=0.0.5 (from pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading tcolorpy-0.1.6-py3-none-any.whl.metadata (6.4 kB)\n",
            "Collecting typepy<2,>=1.3.2 (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm_eval==0.3.0->-r requirements.txt (line 11))\n",
            "  Downloading typepy-1.3.2-py3-none-any.whl.metadata (9.3 kB)\n",
            "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->optimum==1.17.*->-r requirements.txt (line 15)) (1.3.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx>=0.24.1->gradio==4.26.*->-r requirements.txt (line 8)) (1.2.2)\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 29))\n",
            "  Downloading smmap-5.0.1-py3-none-any.whl.metadata (4.3 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 8)) (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 8)) (0.35.1)\n",
            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==4.26.*->-r requirements.txt (line 8)) (0.20.0)\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 11)) (5.2.0)\n",
            "Downloading aqlm-1.1.6-py3-none-any.whl (14 kB)\n",
            "Downloading auto_gptq-0.7.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (23.5 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.5/23.5 MB\u001b[0m \u001b[31m63.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading bitsandbytes-0.43.3-py3-none-manylinux_2_24_x86_64.whl (137.5 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m137.5/137.5 MB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m101.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m11.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m96.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m35.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m18.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading transformers-4.43.4-py3-none-any.whl (9.4 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.4/9.4 MB\u001b[0m \u001b[31m65.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m20.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading flask_cloudflared-0.0.14-py3-none-any.whl (6.4 kB)\n",
            "Downloading sse_starlette-1.6.5-py3-none-any.whl (9.6 kB)\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[31m28.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading tomlkit-0.12.0-py3-none-any.whl (37 kB)\n",
            "Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
            "Downloading datasets-2.21.0-py3-none-any.whl (527 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m527.3/527.3 kB\u001b[0m \u001b[31m39.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading pillow-10.4.0-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[31m88.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading wandb-0.17.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.3 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.3/9.3 MB\u001b[0m \u001b[31m104.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading tiktoken-0.7.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.1 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m58.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading torch-2.2.2-cp310-cp310-manylinux1_x86_64.whl (755.5 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m755.5/755.5 MB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading triton-2.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (167.9 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m167.9/167.9 MB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hUsing cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
            "Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
            "Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
            "Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
            "Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
            "Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
            "Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
            "Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
            "Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
            "Downloading nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.0/166.0 MB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hUsing cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
            "Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\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[31m11.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\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[31m20.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m15.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading openai-1.42.0-py3-none-any.whl (362 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m362.9/362.9 kB\u001b[0m \u001b[31m30.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading orjson-3.10.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (141 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m141.9/141.9 kB\u001b[0m \u001b[31m14.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading pyarrow-17.0.0-cp310-cp310-manylinux_2_28_x86_64.whl (39.9 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m39.9/39.9 MB\u001b[0m \u001b[31m18.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading pybind11-2.13.5-py3-none-any.whl (240 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m241.0/241.0 kB\u001b[0m \u001b[31m18.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading python_multipart-0.0.9-py3-none-any.whl (22 kB)\n",
            "Downloading ruff-0.6.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (10.3 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.3/10.3 MB\u001b[0m \u001b[31m117.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
            "Downloading sentry_sdk-2.13.0-py2.py3-none-any.whl (309 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m309.1/309.1 kB\u001b[0m \u001b[31m22.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading uvicorn-0.30.6-py3-none-any.whl (62 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.8/62.8 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m3.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading fastapi-0.112.2-py3-none-any.whl (93 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m93.5/93.5 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading starlette-0.38.2-py3-none-any.whl (72 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m72.0/72.0 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading fastparquet-2024.5.0-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[31m72.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading ffmpy-0.4.0-py3-none-any.whl (5.8 kB)\n",
            "Downloading gekko-1.2.1-py3-none-any.whl (13.2 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.2/13.2 MB\u001b[0m \u001b[31m93.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading jsonlines-4.0.0-py3-none-any.whl (8.7 kB)\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[31m15.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m25.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading pycountry-24.6.1-py3-none-any.whl (6.3 MB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.3/6.3 MB\u001b[0m \u001b[31m115.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\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[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading rouge-1.0.1-py3-none-any.whl (13 kB)\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",
            "Downloading tqdm_multiprocess-0.0.11-py3-none-any.whl (9.8 kB)\n",
            "Downloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m19.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading zstandard-0.23.0-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[31m96.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m83.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading DataProperty-1.0.1-py3-none-any.whl (27 kB)\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[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading 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[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading jiter-0.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (318 kB)\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m318.9/318.9 kB\u001b[0m \u001b[31m29.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hDownloading mbstrdecoder-1.1.3-py3-none-any.whl (7.8 kB)\n",
            "Downloading pathvalidate-3.2.1-py3-none-any.whl (23 kB)\n",
            "Downloading tabledata-1.3.3-py3-none-any.whl (11 kB)\n",
            "Downloading tcolorpy-0.1.6-py3-none-any.whl (8.1 kB)\n",
            "Downloading typepy-1.3.2-py3-none-any.whl (31 kB)\n",
            "Downloading portalocker-2.10.1-py3-none-any.whl (18 kB)\n",
            "Downloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
            "Using cached nvidia_nvjitlink_cu12-12.6.20-py3-none-manylinux2014_x86_64.whl (19.7 MB)\n",
            "Building wheels for collected packages: hqq, rouge-score, sqlitedict\n",
            "  Building wheel for hqq (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for hqq: filename=hqq-0.1.7.post3-py3-none-any.whl size=59172 sha256=4ea03813c8dcc574b63ae643553d5c4042049534add82887f825d6bfb04b9fd0\n",
            "  Stored in directory: /root/.cache/pip/wheels/e6/48/52/64097324429cfc0c8e47c763b060a132484cdb0a99483ecf82\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=24935 sha256=b3fd56e977bad7548c9067fbc9c4be56274c83742738d43d0e6bcd252b27249e\n",
            "  Stored in directory: /root/.cache/pip/wheels/5f/dd/89/461065a73be61a532ff8599a28e9beef17985c9e9c31e541b4\n",
            "  Building wheel for sqlitedict (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for sqlitedict: filename=sqlitedict-2.1.0-py3-none-any.whl size=16863 sha256=502bdf07863607b5c4b460649fe8034da30f05b44c9724a4d62e483010692d62\n",
            "  Stored in directory: /root/.cache/pip/wheels/79/d6/e7/304e0e6cb2221022c26d8161f7c23cd4f259a9e41e8bbcfabd\n",
            "Successfully built hqq rouge-score sqlitedict\n",
            "Installing collected packages: sqlitedict, pydub, ninja, zstandard, xxhash, websockets, triton, tomlkit, tcolorpy, smmap, setproctitle, sentry-sdk, semantic-version, ruff, rouge, python-multipart, pycountry, pybind11, pyarrow, 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, mbstrdecoder, llvmlite, jsonlines, jiter, humanfriendly, h11, gekko, ffmpy, 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, coloredlogs, sse-starlette, nvidia-cusolver-cu12, httpx, gitpython, flask_cloudflared, fastparquet, fastapi, wandb, transformers, torch, openai, gradio-client, exllamav2, datasets, DataProperty, tabledata, gradio, flash-attn, bitsandbytes, autoawq-kernels, pytablewriter, peft, optimum, hqq, autoawq, aqlm, lm_eval, auto-gptq\n",
            "  Attempting uninstall: triton\n",
            "    Found existing installation: triton 2.3.1\n",
            "    Uninstalling triton-2.3.1:\n",
            "      Successfully uninstalled triton-2.3.1\n",
            "  Attempting uninstall: tomlkit\n",
            "    Found existing installation: tomlkit 0.13.2\n",
            "    Uninstalling tomlkit-0.13.2:\n",
            "      Successfully uninstalled tomlkit-0.13.2\n",
            "  Attempting uninstall: pyarrow\n",
            "    Found existing installation: pyarrow 14.0.2\n",
            "    Uninstalling pyarrow-14.0.2:\n",
            "      Successfully uninstalled pyarrow-14.0.2\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: llvmlite\n",
            "    Found existing installation: llvmlite 0.43.0\n",
            "    Uninstalling llvmlite-0.43.0:\n",
            "      Successfully uninstalled llvmlite-0.43.0\n",
            "  Attempting uninstall: numba\n",
            "    Found existing installation: numba 0.60.0\n",
            "    Uninstalling numba-0.60.0:\n",
            "      Successfully uninstalled numba-0.60.0\n",
            "  Attempting uninstall: transformers\n",
            "    Found existing installation: transformers 4.42.4\n",
            "    Uninstalling transformers-4.42.4:\n",
            "      Successfully uninstalled transformers-4.42.4\n",
            "  Attempting uninstall: torch\n",
            "    Found existing installation: torch 2.3.1+cu121\n",
            "    Uninstalling torch-2.3.1+cu121:\n",
            "      Successfully uninstalled torch-2.3.1+cu121\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",
            "cudf-cu12 24.4.1 requires pyarrow<15.0.0a0,>=14.0.1, but you have pyarrow 17.0.0 which is incompatible.\n",
            "ibis-framework 8.0.0 requires pyarrow<16,>=2, but you have pyarrow 17.0.0 which is incompatible.\n",
            "torchaudio 2.3.1+cu121 requires torch==2.3.1, but you have torch 2.2.2 which is incompatible.\n",
            "torchtext 0.18.0 requires torch>=2.3.0, but you have torch 2.2.2 which is incompatible.\n",
            "torchvision 0.18.1+cu121 requires torch==2.3.1, but you have torch 2.2.2 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed DataProperty-1.0.1 Pillow-10.4.0 SpeechRecognition-3.10.0 aiofiles-23.2.1 aqlm-1.1.6 auto-gptq-0.7.1 autoawq-0.2.6 autoawq-kernels-0.0.7 bitsandbytes-0.43.3 colorama-0.4.6 coloredlogs-15.0.1 cramjam-2.8.3 datasets-2.21.0 dill-0.3.8 diskcache-5.6.3 docker-pycreds-0.4.0 exllamav2-0.1.8+cu121.torch2.2.2 fastapi-0.112.2 fastparquet-2024.5.0 ffmpy-0.4.0 flash-attn-2.6.1 flask_cloudflared-0.0.14 gekko-1.2.1 gitdb-4.0.11 gitpython-3.1.43 gradio-4.26.0 gradio-client-0.15.1 h11-0.14.0 hqq-0.1.7.post3 httpcore-1.0.5 httpx-0.27.0 humanfriendly-10.0 jiter-0.5.0 jsonlines-4.0.0 llama-cpp-python-0.2.85+cpuavx2 llama-cpp-python-cuda-0.2.85+cu121 llama-cpp-python-cuda-tensorcores-0.2.85+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 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-cu12-12.6.20 nvidia-nvtx-cu12-12.1.105 openai-1.42.0 optimum-1.17.1 orjson-3.10.7 pathvalidate-3.2.1 peft-0.8.2 portalocker-2.10.1 pyarrow-17.0.0 pybind11-2.13.5 pycountry-24.6.1 pydub-0.25.1 pytablewriter-1.2.0 python-multipart-0.0.9 rouge-1.0.1 rouge-score-0.1.2 ruff-0.6.2 sacrebleu-1.5.0 semantic-version-2.10.0 sentry-sdk-2.13.0 setproctitle-1.3.3 smmap-5.0.1 sqlitedict-2.1.0 sse-starlette-1.6.5 starlette-0.38.2 tabledata-1.3.3 tcolorpy-0.1.6 tiktoken-0.7.0 tomlkit-0.12.0 torch-2.2.2 tqdm-multiprocess-0.0.11 transformers-4.43.4 triton-2.2.0 typepy-1.3.2 uvicorn-0.30.6 wandb-0.17.7 websockets-11.0.3 xxhash-3.5.0 zstandard-0.23.0\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "PIL"
                ]
              },
              "id": "0cda441691304d43b9de709d9a44cbb1"
            }
          },
          "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) (0.112.2)\n",
            "Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.4.0)\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) (0.23.5)\n",
            "Requirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (6.4.3)\n",
            "Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (3.1.4)\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) (3.10.7)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (24.1)\n",
            "Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (2.1.4)\n",
            "Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (10.4.0)\n",
            "Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (2.8.2)\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) (6.0.2)\n",
            "Requirement already satisfied: ruff>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.6.2)\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<1.0,>=0.9 in /usr/local/lib/python3.10/dist-packages (from typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio==4.26.0) (0.12.4)\n",
            "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (4.12.2)\n",
            "Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio==4.26.0) (0.30.6)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.15.1->gradio==4.26.0) (2024.6.1)\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) (4.23.0)\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) (2024.7.4)\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) (3.15.4)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio==4.26.0) (2.32.3)\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) (4.66.5)\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) (4.53.1)\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) (2024.1)\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) (0.7.0)\n",
            "Requirement already satisfied: pydantic-core==2.20.1 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio==4.26.0) (2.20.1)\n",
            "Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.9->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio==4.26.0) (8.1.7)\n",
            "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.9->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio==4.26.0) (1.5.4)\n",
            "Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.9->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio==4.26.0) (13.7.1)\n",
            "\u001b[33mWARNING: typer 0.12.4 does not provide the extra 'all'\u001b[0m\u001b[33m\n",
            "\u001b[0mRequirement already satisfied: starlette<0.39.0,>=0.37.2 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio==4.26.0) (0.38.2)\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) (24.2.0)\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) (0.35.1)\n",
            "Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==4.26.0) (0.20.0)\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>=10.11.0->typer<1.0,>=0.9->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->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>=10.11.0->typer<1.0,>=0.9->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->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) (1.2.2)\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>=10.11.0->typer<1.0,>=0.9->typer[all]<1.0,>=0.9; sys_platform != \"emscripten\"->gradio==4.26.0) (0.1.2)\n",
            "\u001b[0m\n",
            "Download Results:\n",
            "gid   |stat|avg speed  |path/URI\n",
            "======+====+===========+=======================================================\n",
            "3bee37|\u001b[1;32mOK\u001b[0m  |   163MiB/s|/content/text-generation-webui/models//Mistral-NeMo-Minitron-8B-Base.Q5_K_M.gguf\n",
            "\n",
            "Status Legend:\n",
            "(OK):download completed.\n",
            "/content/text-generation-webui\n",
            "\u001b[2;36m07:04:50-844954\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Starting Text generation web UI                                            \n",
            "\u001b[2;36m07:04:51-274414\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Loading \u001b[32m\"Mistral-NeMo-Minitron-8B-Base.Q5_K_M.gguf\"\u001b[0m                        \n",
            "\u001b[2;36m07:04:51-664489\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m llama.cpp weights detected:                                                \n",
            "\u001b[2;36m                \u001b[0m         \u001b[32m\"models/Mistral-NeMo-Minitron-8B-Base.Q5_K_M.gguf\"\u001b[0m                         \n",
            "llama_model_loader: loaded meta data with 35 key-value pairs and 363 tensors from models/Mistral-NeMo-Minitron-8B-Base.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.type str              = model\n",
            "llama_model_loader: - kv   2:                               general.name str              = Mistral NeMo Minitron 8B Base\n",
            "llama_model_loader: - kv   3:                       general.organization str              = Nvidia\n",
            "llama_model_loader: - kv   4:                           general.finetune str              = Base\n",
            "llama_model_loader: - kv   5:                           general.basename str              = Mistral-NeMo-Minitron\n",
            "llama_model_loader: - kv   6:                         general.size_label str              = 8B\n",
            "llama_model_loader: - kv   7:                            general.license str              = other\n",
            "llama_model_loader: - kv   8:                       general.license.name str              = nvidia-open-model-license\n",
            "llama_model_loader: - kv   9:                       general.license.link str              = https://developer.download.nvidia.com...\n",
            "llama_model_loader: - kv  10:                          llama.block_count u32              = 40\n",
            "llama_model_loader: - kv  11:                       llama.context_length u32              = 8192\n",
            "llama_model_loader: - kv  12:                     llama.embedding_length u32              = 4096\n",
            "llama_model_loader: - kv  13:                  llama.feed_forward_length u32              = 11520\n",
            "llama_model_loader: - kv  14:                 llama.attention.head_count u32              = 32\n",
            "llama_model_loader: - kv  15:              llama.attention.head_count_kv u32              = 8\n",
            "llama_model_loader: - kv  16:                       llama.rope.freq_base f32              = 1000000.000000\n",
            "llama_model_loader: - kv  17:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010\n",
            "llama_model_loader: - kv  18:                 llama.attention.key_length u32              = 128\n",
            "llama_model_loader: - kv  19:               llama.attention.value_length u32              = 128\n",
            "llama_model_loader: - kv  20:                          general.file_type u32              = 17\n",
            "llama_model_loader: - kv  21:                           llama.vocab_size u32              = 131072\n",
            "llama_model_loader: - kv  22:                 llama.rope.dimension_count u32              = 128\n",
            "llama_model_loader: - kv  23:            tokenizer.ggml.add_space_prefix bool             = false\n",
            "llama_model_loader: - kv  24:                       tokenizer.ggml.model str              = gpt2\n",
            "llama_model_loader: - kv  25:                         tokenizer.ggml.pre str              = tekken\n",
            "llama_model_loader: - kv  26:                      tokenizer.ggml.tokens arr[str,131072]  = [\"<unk>\", \"<s>\", \"</s>\", \"[INST]\", \"[...\n",
            "llama_model_loader: - kv  27:                  tokenizer.ggml.token_type arr[i32,131072]  = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ...\n",
            "Exception ignored on calling ctypes callback function: <function llama_log_callback at 0x7a706f4c3a30>\n",
            "Traceback (most recent call last):\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/llama_cpp_cuda/_logger.py\", line 30, in llama_log_callback\n",
            "    print(text.decode(\"utf-8\"), end=\"\", flush=True, file=sys.stderr)\n",
            "UnicodeDecodeError: 'utf-8' codec can't decode byte 0xc4 in position 128: invalid continuation byte\n",
            "llama_model_loader: - kv  29:                tokenizer.ggml.bos_token_id u32              = 1\n",
            "llama_model_loader: - kv  30:                tokenizer.ggml.eos_token_id u32              = 2\n",
            "llama_model_loader: - kv  31:            tokenizer.ggml.unknown_token_id u32              = 0\n",
            "llama_model_loader: - kv  32:               tokenizer.ggml.add_bos_token bool             = true\n",
            "llama_model_loader: - kv  33:               tokenizer.ggml.add_eos_token bool             = false\n",
            "llama_model_loader: - kv  34:               general.quantization_version u32              = 2\n",
            "llama_model_loader: - type  f32:   81 tensors\n",
            "llama_model_loader: - type q5_K:  241 tensors\n",
            "llama_model_loader: - type q6_K:   41 tensors\n",
            "llm_load_vocab: special tokens cache size = 1000\n",
            "llm_load_vocab: token to piece cache size = 0.8498 MB\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          = 131072\n",
            "llm_load_print_meta: n_merges         = 269443\n",
            "llm_load_print_meta: vocab_only       = 0\n",
            "llm_load_print_meta: n_ctx_train      = 8192\n",
            "llm_load_print_meta: n_embd           = 4096\n",
            "llm_load_print_meta: n_layer          = 40\n",
            "llm_load_print_meta: n_head           = 32\n",
            "llm_load_print_meta: n_head_kv        = 8\n",
            "llm_load_print_meta: n_rot            = 128\n",
            "llm_load_print_meta: n_swa            = 0\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             = 11520\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  = 1000000.0\n",
            "llm_load_print_meta: freq_scale_train = 1\n",
            "llm_load_print_meta: n_ctx_orig_yarn  = 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       = 13B\n",
            "llm_load_print_meta: model ftype      = Q5_K - Medium\n",
            "llm_load_print_meta: model params     = 8.41 B\n",
            "llm_load_print_meta: model size       = 5.58 GiB (5.70 BPW) \n",
            "llm_load_print_meta: general.name     = Mistral NeMo Minitron 8B Base\n",
            "llm_load_print_meta: BOS token        = 1 '<s>'\n",
            "llm_load_print_meta: EOS token        = 2 '</s>'\n",
            "llm_load_print_meta: UNK token        = 0 '<unk>'\n",
            "llm_load_print_meta: LF token         = 1196 'Ä'\n",
            "llm_load_print_meta: max token length = 150\n",
            "ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    yes\n",
            "ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: 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 =    0.34 MiB\n",
            "llm_load_tensors: offloading 40 repeating layers to GPU\n",
            "llm_load_tensors: offloading non-repeating layers to GPU\n",
            "llm_load_tensors: offloaded 41/41 layers to GPU\n",
            "llm_load_tensors:        CPU buffer size =   352.00 MiB\n",
            "llm_load_tensors:      CUDA0 buffer size =  5363.93 MiB\n",
            ".........................................................................................\n",
            "llama_new_context_with_model: n_ctx      = 8224\n",
            "llama_new_context_with_model: n_batch    = 512\n",
            "llama_new_context_with_model: n_ubatch   = 512\n",
            "llama_new_context_with_model: flash_attn = 0\n",
            "llama_new_context_with_model: freq_base  = 1000000.0\n",
            "llama_new_context_with_model: freq_scale = 1\n",
            "llama_kv_cache_init:      CUDA0 KV buffer size =  1285.00 MiB\n",
            "llama_new_context_with_model: KV self size  = 1285.00 MiB, K (f16):  642.50 MiB, V (f16):  642.50 MiB\n",
            "llama_new_context_with_model:  CUDA_Host  output buffer size =     0.50 MiB\n",
            "llama_new_context_with_model:      CUDA0 compute buffer size =   562.07 MiB\n",
            "llama_new_context_with_model:  CUDA_Host compute buffer size =    24.07 MiB\n",
            "llama_new_context_with_model: graph nodes  = 1286\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 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | \n",
            "Model metadata: {'general.quantization_version': '2', 'llama.embedding_length': '4096', 'general.license': 'other', 'llama.attention.value_length': '128', 'general.license.name': 'nvidia-open-model-license', 'tokenizer.ggml.add_bos_token': 'true', 'general.size_label': '8B', 'general.type': 'model', 'tokenizer.ggml.add_eos_token': 'false', 'general.organization': 'Nvidia', 'llama.context_length': '8192', 'general.basename': 'Mistral-NeMo-Minitron', 'llama.attention.head_count_kv': '8', 'general.architecture': 'llama', 'llama.feed_forward_length': '11520', 'general.name': 'Mistral NeMo Minitron 8B Base', 'tokenizer.ggml.bos_token_id': '1', 'llama.rope.freq_base': '1000000.000000', 'llama.block_count': '40', 'llama.attention.head_count': '32', 'llama.attention.key_length': '128', 'general.finetune': 'Base', 'general.file_type': '17', 'general.license.link': 'https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf', 'tokenizer.ggml.pre': 'tekken', 'llama.vocab_size': '131072', 'llama.rope.dimension_count': '128', 'tokenizer.ggml.add_space_prefix': 'false', 'tokenizer.ggml.model': 'gpt2', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'tokenizer.ggml.eos_token_id': '2', 'tokenizer.ggml.unknown_token_id': '0'}\n",
            "Using fallback chat format: llama-2\n",
            "\u001b[2;36m07:05:13-363107\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Loaded \u001b[32m\"Mistral-NeMo-Minitron-8B-Base.Q5_K_M.gguf\"\u001b[0m in \u001b[1;36m22.09\u001b[0m seconds.       \n",
            "\u001b[2;36m07:05:13-364569\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m LOADER: \u001b[32m\"llama.cpp\"\u001b[0m                                                        \n",
            "\u001b[2;36m07:05:13-365517\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m TRUNCATION LENGTH: \u001b[1;36m8196\u001b[0m                                                    \n",
            "\u001b[2;36m07:05:13-366499\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m INSTRUCTION TEMPLATE: \u001b[32m\"Alpaca\"\u001b[0m                                             \n",
            "\n",
            "Running on local URL:  http://127.0.0.1:7860\n",
            "\n",
            "Running on public URL: https://f77624db364256d0d4.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 =     555.28 ms\n",
            "llama_print_timings:      sample time =    9418.51 ms /  1024 runs   (    9.20 ms per token,   108.72 tokens per second)\n",
            "llama_print_timings: prompt eval time =     554.42 ms /    20 tokens (   27.72 ms per token,    36.07 tokens per second)\n",
            "llama_print_timings:        eval time =   30513.69 ms /  1023 runs   (   29.83 ms per token,    33.53 tokens per second)\n",
            "llama_print_timings:       total time =   57042.36 ms /  1043 tokens\n",
            "Output generated in 57.67 seconds (17.76 tokens/s, 1024 tokens, context 26, seed 688334159)\n",
            "Llama.generate: prefix-match hit\n",
            "Output generated in 8.41 seconds (18.08 tokens/s, 152 tokens, context 29, seed 995334177)\n",
            "Llama.generate: prefix-match hit\n",
            "Output generated in 11.76 seconds (17.69 tokens/s, 208 tokens, context 24, seed 488976409)\n",
            "Llama.generate: prefix-match hit\n",
            "Output generated in 15.88 seconds (17.82 tokens/s, 283 tokens, context 37, seed 1385362016)\n",
            "Llama.generate: prefix-match hit\n",
            "Output generated in 54.91 seconds (17.03 tokens/s, 935 tokens, context 73, seed 1235605886)\n",
            "Llama.generate: prefix-match hit\n",
            "Output generated in 18.98 seconds (16.54 tokens/s, 314 tokens, context 841, seed 739068620)\n"
          ]
        }
      ],
      "source": [
        "%cd /content\n",
        "!apt-get -y install -qq aria2\n",
        "\n",
        "!git clone -b V20240819 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",
        "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/QuantFactory/Mistral-NeMo-Minitron-8B-Base-GGUF/resolve/main/Mistral-NeMo-Minitron-8B-Base.Q5_K_M.gguf?download=true -d /content/text-generation-webui/models/ -o Mistral-NeMo-Minitron-8B-Base.Q5_K_M.gguf\n",
        "\n",
        "%cd /content/text-generation-webui\n",
        "!python server.py --share --n-gpu-layers 100000 --model Mistral-NeMo-Minitron-8B-Base.Q5_K_M.gguf --n_ctx 8196"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyOWR2uPGHOMw9ctRDHT0R75",
      "include_colab_link": true
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}