colabs/AutoTrain_LLM.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "cellView": "form",
        "collapsed": true,
        "id": "JvMRbVLEJlZT"
      },
      "outputs": [],
      "source": [
        "#@title 🤗 AutoTrain LLM\n",
        "#@markdown In order to use this colab\n",
        "#@markdown - upload train.csv to a folder named `data/`\n",
        "#@markdown - train.csv must contain a `text` column\n",
        "#@markdown - choose a project name if you wish\n",
        "#@markdown - change model if you wish, you can use most of the text-generation models from Hugging Face Hub\n",
        "#@markdown - add huggingface information (token) if you wish to push trained model to huggingface hub\n",
        "#@markdown - update hyperparameters if you wish\n",
        "#@markdown - click `Runtime > Run all` or run each cell individually\n",
        "#@markdown - report issues / feature requests here: https://github.com/huggingface/autotrain-advanced/issues\n",
        "\n",
        "\n",
        "import os\n",
        "!pip install -U autotrain-advanced > install_logs.txt 2>&1\n",
        "!autotrain setup --colab > setup_logs.txt\n",
        "from autotrain import __version__\n",
        "print(f'AutoTrain version: {__version__}')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "cellView": "form",
        "id": "A2-_lkBS1WKA"
      },
      "outputs": [],
      "source": [
        "#@markdown ---\n",
        "#@markdown #### Project Config\n",
        "#@markdown Note: if you are using a restricted/private model, you need to enter your Hugging Face token in the next step.\n",
        "project_name = 'my-autotrain-llm' # @param {type:\"string\"}\n",
        "model_name = 'abhishek/llama-2-7b-hf-small-shards' # @param {type:\"string\"}\n",
        "\n",
        "#@markdown ---\n",
        "#@markdown #### Push to Hub?\n",
        "#@markdown Use these only if you want to push your trained model to a private repo in your Hugging Face Account\n",
        "#@markdown If you dont use these, the model will be saved in Google Colab and you are required to download it manually.\n",
        "#@markdown Please enter your Hugging Face write token. The trained model will be saved to your Hugging Face account.\n",
        "#@markdown You can find your token here: https://huggingface.co/settings/tokens\n",
        "push_to_hub = False # @param [\"False\", \"True\"] {type:\"raw\"}\n",
        "hf_token = \"hf_XXX\" #@param {type:\"string\"}\n",
        "hf_username = \"abc\" #@param {type:\"string\"}\n",
        "\n",
        "#@markdown ---\n",
        "#@markdown #### Hyperparameters\n",
        "unsloth = False # @param [\"False\", \"True\"] {type:\"raw\"}\n",
        "learning_rate = 2e-4 # @param {type:\"number\"}\n",
        "num_epochs = 1 #@param {type:\"number\"}\n",
        "batch_size = 1 # @param {type:\"slider\", min:1, max:32, step:1}\n",
        "block_size = 1024 # @param {type:\"number\"}\n",
        "trainer = \"sft\" # @param [\"generic\", \"sft\"] {type:\"string\"}\n",
        "warmup_ratio = 0.1 # @param {type:\"number\"}\n",
        "weight_decay = 0.01 # @param {type:\"number\"}\n",
        "gradient_accumulation = 4 # @param {type:\"number\"}\n",
        "mixed_precision = \"fp16\" # @param [\"fp16\", \"bf16\", \"none\"] {type:\"string\"}\n",
        "peft = True # @param [\"False\", \"True\"] {type:\"raw\"}\n",
        "quantization = \"int4\" # @param [\"int4\", \"int8\", \"none\"] {type:\"string\"}\n",
        "lora_r = 16 #@param {type:\"number\"}\n",
        "lora_alpha = 32 #@param {type:\"number\"}\n",
        "lora_dropout = 0.05 #@param {type:\"number\"}\n",
        "\n",
        "os.environ[\"HF_TOKEN\"] = hf_token\n",
        "os.environ[\"HF_USERNAME\"] = hf_username\n",
        "\n",
        "conf = f\"\"\"\n",
        "task: llm-{trainer}\n",
        "base_model: {model_name}\n",
        "project_name: {project_name}\n",
        "log: tensorboard\n",
        "backend: local\n",
        "\n",
        "data:\n",
        "  path: data/\n",
        "  train_split: train\n",
        "  valid_split: null\n",
        "  chat_template: null\n",
        "  column_mapping:\n",
        "    text_column: text\n",
        "\n",
        "params:\n",
        "  block_size: {block_size}\n",
        "  lr: {learning_rate}\n",
        "  warmup_ratio: {warmup_ratio}\n",
        "  weight_decay: {weight_decay}\n",
        "  epochs: {num_epochs}\n",
        "  batch_size: {batch_size}\n",
        "  gradient_accumulation: {gradient_accumulation}\n",
        "  mixed_precision: {mixed_precision}\n",
        "  peft: {peft}\n",
        "  quantization: {quantization}\n",
        "  lora_r: {lora_r}\n",
        "  lora_alpha: {lora_alpha}\n",
        "  lora_dropout: {lora_dropout}\n",
        "  unsloth: {unsloth}\n",
        "\n",
        "hub:\n",
        "  username: ${{HF_USERNAME}}\n",
        "  token: ${{HF_TOKEN}}\n",
        "  push_to_hub: {push_to_hub}\n",
        "\"\"\"\n",
        "\n",
        "with open(\"conf.yaml\", \"w\") as f:\n",
        "  f.write(conf)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": true,
        "id": "g3cd_ED_yXXt"
      },
      "outputs": [],
      "source": [
        "!autotrain --config conf.yaml"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.10.14"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}