{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "21111b1f-7cce-4e8b-8337-8f0cdab5804e",
   "metadata": {},
   "source": [
    "# AutoTrain"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd09a9fd-4b90-48f3-b61c-d2349eb7f43e",
   "metadata": {},
   "source": [
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "52543575-f92e-4038-ad13-30967f47eb7a",
   "metadata": {
    "jupyter": {
     "is_executing": true
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import subprocess\n",
    "\n",
    "import yaml"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "74987944-abfb-44f8-9331-ffbb2f7698bb",
   "metadata": {},
   "source": [
    "## Config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6992324b-173c-4335-b557-cf78fbb2dd93",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b5b27c90c4e849e6aa04587d526e108f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co./front/assets/huggingface_logo-noborder.sv…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from huggingface_hub import login, get_token, whoami\n",
    "login()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "97c25070-775a-4fb1-9694-4579250686a6",
   "metadata": {},
   "source": [
    "### Template\n",
    "Im creating a template so we can iterate through each of our experiments.\n",
    "\n",
    "Here you can see a few design decisions:\n",
    "- We leave `project_name` and `text_column` empty to overwrite later per experiment\n",
    "- We log in tensorboard, you can use wandb, but you will need to install it in the AutoTrain env that is run on spaces, which gets complex\n",
    "- I choose an `l4x1` from [these options](https://github.com/huggingface/autotrain-advanced/blob/2d787b2033414d06f1e9be2ea0caacad3097f5e8/src/autotrain/backends/base.py#L21)\n",
    "    - This is a [well priced](https://huggingface.co./pricing#spaces) way of training a 7B moodel \n",
    "    - It's very efficient as well at 24GB VRAM\n",
    "- It's becoming less common to use a `valid_split` \n",
    "- I run 2 epochs as the loss still decreases steadily, but some say for LoRAs you should just do 1\n",
    "- Its a good idea use `all-linear` when using LoRA "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "dc2a8514-51c1-404b-8cfa-6637cc810668",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Base config\n",
    "config_template = {\n",
    "    \"task\": \"llm-sft\",\n",
    "    \"base_model\": \"tiiuae/Falcon3-7B-Instruct\",\n",
    "    \"project_name\": \"\",\n",
    "    \"log\": \"tensorboard\",\n",
    "    \"backend\": \"spaces-a100-large\",\n",
    "    \"data\": {\n",
    "        \"path\": \"derek-thomas/labeled-multiple-choice-explained-falcon-tokenized\",\n",
    "        \"train_split\": \"train\",\n",
    "        \"valid_split\": None,\n",
    "        \"chat_template\": \"tokenizer\",\n",
    "        \"column_mapping\": {\n",
    "            \"text_column\": \"\"\n",
    "            },\n",
    "        },\n",
    "    \"params\": {\n",
    "        \"block_size\": 512,\n",
    "        \"model_max_length\": 1750,\n",
    "        \"epochs\": 4,\n",
    "        \"batch_size\": 8,\n",
    "        \"lr\": 5e-5,\n",
    "        \"peft\": True,\n",
    "        \"quantization\": \"int4\",\n",
    "        \"target_modules\": \"all-linear\",\n",
    "        \"padding\": \"right\",\n",
    "        \"optimizer\": \"adamw_torch\",\n",
    "        \"scheduler\": \"linear\",\n",
    "        \"gradient_accumulation\": 8,\n",
    "        \"mixed_precision\": \"bf16\",\n",
    "        },\n",
    "    \"hub\": {\n",
    "        \"username\": \"derek-thomas\",\n",
    "        \"token\": get_token(),\n",
    "        \"push_to_hub\": True,\n",
    "        },\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "22eb3d3a-0ab0-4f79-98c2-513a34ce1b6d",
   "metadata": {},
   "source": [
    "### Experiments\n",
    "Here we choose the `project_name` and `text_column` for each experiment."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "957eb2b7-feec-422f-ba46-b293d9a77c1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "project_suffixes = [\"RFA-gpt3-5\", \"RFA-falcon\", \"FAR-gpt3-5\", \"FAR-falcon\", \"FA\"]\n",
    "text_columns = [\"conversation_RFA_gpt3_5\", \"conversation_RFA_falcon\", \"conversation_FAR_gpt3_5\",\n",
    "                \"conversation_FAR_falcon\", \"conversation_FA\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a5913085-83c9-4133-a90d-318fd13cc14e",
   "metadata": {},
   "source": [
    "Directory to store generated configs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b86702bf-f494-4951-863e-be5b8462fbd1",
   "metadata": {},
   "outputs": [],
   "source": [
    "output_dir = \"./autotrain_configs\"\n",
    "os.makedirs(output_dir, exist_ok=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3053d1e1-ca40-460c-8999-0787a1751d00",
   "metadata": {},
   "source": [
    "## AutoTrain for each Experiment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "025ccd2f-de54-4ac2-9f36-f606876dcd3c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running autotrain with config: ./autotrain_configs/conversation_RFA_gpt3_5.yml\n",
      "INFO     | 2025-01-10 13:45:51 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_RFA_gpt3_5.yml\n",
      "INFO     | 2025-01-10 13:45:51 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
      "INFO     | 2025-01-10 13:45:51 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
      "INFO     | 2025-01-10 13:45:51 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-RFA-gpt3-5', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_RFA_gpt3_5', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
      "INFO     | 2025-01-10 13:45:54 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5\n",
      "\n",
      "---\n",
      "https://huggingface.co./spaces/derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5\n",
      "---\n",
      "\n",
      "Running autotrain with config: ./autotrain_configs/conversation_RFA_falcon.yml\n",
      "INFO     | 2025-01-10 13:45:58 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_RFA_falcon.yml\n",
      "INFO     | 2025-01-10 13:45:58 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
      "INFO     | 2025-01-10 13:45:58 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
      "INFO     | 2025-01-10 13:45:58 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-RFA-falcon', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_RFA_falcon', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
      "INFO     | 2025-01-10 13:46:01 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-RFA-falcon\n",
      "\n",
      "---\n",
      "https://huggingface.co./spaces/derek-thomas/autotrain-falcon-v03-poe-RFA-falcon\n",
      "---\n",
      "\n",
      "Running autotrain with config: ./autotrain_configs/conversation_FAR_gpt3_5.yml\n",
      "INFO     | 2025-01-10 13:46:05 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FAR_gpt3_5.yml\n",
      "INFO     | 2025-01-10 13:46:05 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
      "INFO     | 2025-01-10 13:46:05 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
      "INFO     | 2025-01-10 13:46:05 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FAR-gpt3-5', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FAR_gpt3_5', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
      "INFO     | 2025-01-10 13:46:08 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5\n",
      "\n",
      "---\n",
      "https://huggingface.co./spaces/derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5\n",
      "---\n",
      "\n",
      "Running autotrain with config: ./autotrain_configs/conversation_FAR_falcon.yml\n",
      "INFO     | 2025-01-10 13:46:13 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FAR_falcon.yml\n",
      "INFO     | 2025-01-10 13:46:13 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
      "INFO     | 2025-01-10 13:46:13 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
      "INFO     | 2025-01-10 13:46:13 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FAR-falcon', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FAR_falcon', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
      "INFO     | 2025-01-10 13:46:16 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FAR-falcon\n",
      "\n",
      "---\n",
      "https://huggingface.co./spaces/derek-thomas/autotrain-falcon-v03-poe-FAR-falcon\n",
      "---\n",
      "\n",
      "Running autotrain with config: ./autotrain_configs/conversation_FA.yml\n",
      "INFO     | 2025-01-10 13:46:20 | autotrain.cli.autotrain:main:58 - Using AutoTrain configuration: ./autotrain_configs/conversation_FA.yml\n",
      "INFO     | 2025-01-10 13:46:20 | autotrain.parser:__post_init__:165 - Running task: lm_training\n",
      "INFO     | 2025-01-10 13:46:20 | autotrain.parser:__post_init__:166 - Using backend: spaces-a100-large\n",
      "INFO     | 2025-01-10 13:46:20 | autotrain.parser:run:224 - {'model': 'tiiuae/Falcon3-7B-Instruct', 'project_name': 'falcon-v03-poe-FA', 'data_path': 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized', 'train_split': 'train', 'valid_split': None, 'add_eos_token': True, 'block_size': 512, 'model_max_length': 1750, 'padding': 'right', 'trainer': 'sft', 'use_flash_attention_2': False, 'log': 'tensorboard', 'disable_gradient_checkpointing': False, 'logging_steps': -1, 'eval_strategy': 'epoch', 'save_total_limit': 1, 'auto_find_batch_size': False, 'mixed_precision': 'bf16', 'lr': 5e-05, 'epochs': 4, 'batch_size': 8, 'warmup_ratio': 0.1, 'gradient_accumulation': 8, 'optimizer': 'adamw_torch', 'scheduler': 'linear', 'weight_decay': 0.0, 'max_grad_norm': 1.0, 'seed': 42, 'chat_template': 'tokenizer', 'quantization': 'int4', 'target_modules': 'all-linear', 'merge_adapter': False, 'peft': True, 'lora_r': 16, 'lora_alpha': 32, 'lora_dropout': 0.05, 'model_ref': None, 'dpo_beta': 0.1, 'max_prompt_length': 128, 'max_completion_length': None, 'prompt_text_column': None, 'text_column': 'conversation_FA', 'rejected_text_column': None, 'push_to_hub': True, 'username': 'derek-thomas', 'token': '*****', 'unsloth': False, 'distributed_backend': None}\n",
      "INFO     | 2025-01-10 13:46:23 | autotrain.parser:run:229 - Job ID: derek-thomas/autotrain-falcon-v03-poe-FA\n",
      "\n",
      "---\n",
      "https://huggingface.co./spaces/derek-thomas/autotrain-falcon-v03-poe-FA\n",
      "---\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Generate configs and run commands\n",
    "autotrain_spaces = []\n",
    "autotrain_models = []\n",
    "for project_suffix, text_column in zip(project_suffixes, text_columns):\n",
    "    # Modify the config\n",
    "    config = config_template.copy()\n",
    "    config[\"project_name\"] = f\"falcon-v03-poe-{project_suffix}\"\n",
    "    config[\"data\"][\"column_mapping\"][\"text_column\"] = text_column\n",
    "\n",
    "    # Save the config to a YAML file\n",
    "    config_path = os.path.join(output_dir, f\"{text_column}.yml\")\n",
    "    with open(config_path, \"w\") as f:\n",
    "        yaml.dump(config, f)\n",
    "\n",
    "    # # Run the command\n",
    "    print(f\"Running autotrain with config: {config_path}\")\n",
    "    subprocess.run([\"autotrain\", \"--config\", config_path])\n",
    "\n",
    "    space_name = f\"{whoami()['name']}/autotrain-{config['project_name']}\"\n",
    "    model_name = f\"{whoami()['name']}/{config['project_name']}\"\n",
    "    autotrain_spaces.append(space_name)\n",
    "    autotrain_models.append(model_name)\n",
    "    print(f'\\n---\\nhttps://huggingface.co./spaces/{space_name}\\n---\\n')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bf3d3324-202b-45df-8897-58cf89931c45",
   "metadata": {},
   "source": [
    "# Cleanup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "adf09687-ab1e-4f1e-8bf9-317cc928467a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from huggingface_hub import HfApi\n",
    "api = HfApi()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "19d80d26-cda4-41fb-a125-06060c3f90ce",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5',\n",
      " 'derek-thomas/autotrain-falcon-v03-poe-RFA-falcon',\n",
      " 'derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5',\n",
      " 'derek-thomas/autotrain-falcon-v03-poe-FAR-falcon',\n",
      " 'derek-thomas/autotrain-falcon-v03-poe-FA']\n",
      "\n",
      "['derek-thomas/falcon-v03-poe-RFA-gpt3-5',\n",
      " 'derek-thomas/falcon-v03-poe-RFA-falcon',\n",
      " 'derek-thomas/falcon-v03-poe-FAR-gpt3-5',\n",
      " 'derek-thomas/falcon-v03-poe-FAR-falcon',\n",
      " 'derek-thomas/falcon-v03-poe-FA']\n"
     ]
    }
   ],
   "source": [
    "from pprint import pprint\n",
    "pprint(autotrain_spaces)\n",
    "print()\n",
    "pprint(autotrain_models)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0040e05b-39c2-4aff-a40e-01577a388eff",
   "metadata": {},
   "source": [
    "<span style=\"color:red; font-size:20px; font-weight:bold;\">\n",
    "WAIT TO RUN THIS UNTIL YOUR SPACES ARE FINISHED TRAINING!\n",
    "</span>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "de150f086f1c72fa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/autotrain-falcon-v03-poe-RFA-gpt3-5\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-RFA-falcon'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/autotrain-falcon-v03-poe-RFA-falcon\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/autotrain-falcon-v03-poe-FAR-gpt3-5\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-FAR-falcon'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/autotrain-falcon-v03-poe-FAR-falcon\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the space 'derek-thomas/autotrain-falcon-v03-poe-FA'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/autotrain-falcon-v03-poe-FA\n"
     ]
    }
   ],
   "source": [
    "for space in autotrain_spaces:\n",
    "    confirm = input(f\"Are you sure you want to delete the space '{space}'? (y/n): \")\n",
    "    if confirm.lower() == 'y':\n",
    "        api.delete_repo(space, repo_type='space')\n",
    "        print(f\"Deleted {space}\")\n",
    "    else:\n",
    "        print(f\"Skipped {space}\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e6aa4788fe8b0297",
   "metadata": {},
   "source": [
    "<span style=\"color:red; font-size:20px; font-weight:bold;\">\n",
    "ONLY RUN THIS IF YOU NEED TO RESTART FROM SCRATCH\n",
    "THIS WILL DELETE YOUR MODELS\n",
    "</span>\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c887e61558785e69",
   "metadata": {},
   "outputs": [
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-RFA-gpt3-5'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/falcon-v03-poe-RFA-gpt3-5\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-RFA-falcon'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/falcon-v03-poe-RFA-falcon\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-FAR-gpt3-5'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/falcon-v03-poe-FAR-gpt3-5\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-FAR-falcon'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/falcon-v03-poe-FAR-falcon\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to delete the model 'derek-thomas/falcon-v03-poe-FA'? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Deleted derek-thomas/falcon-v03-poe-FA\n"
     ]
    }
   ],
   "source": [
    "for model in autotrain_models:\n",
    "    confirm = input(f\"Are you sure you want to delete the model '{model}'? (y/n): \")\n",
    "    if confirm.lower() == 'y':\n",
    "        api.delete_repo(model, repo_type='model')\n",
    "        print(f\"Deleted {model}\")\n",
    "    else:\n",
    "        print(f\"Skipped {model}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "a8a8d4c2-0fb5-438c-9fbf-436144d05543",
   "metadata": {},
   "outputs": [
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to move the model from 'derek-thomas/falcon-v03-poe-RFA-gpt3-5' to derek-thomas/falcon-v03-poe-RFA-gpt3-5_backup? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Moved derek-thomas/falcon-v03-poe-RFA-gpt3-5 to derek-thomas/falcon-v03-poe-RFA-gpt3-5_backup\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to move the model from 'derek-thomas/falcon-v03-poe-RFA-falcon' to derek-thomas/falcon-v03-poe-RFA-falcon_backup? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Moved derek-thomas/falcon-v03-poe-RFA-falcon to derek-thomas/falcon-v03-poe-RFA-falcon_backup\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to move the model from 'derek-thomas/falcon-v03-poe-FAR-gpt3-5' to derek-thomas/falcon-v03-poe-FAR-gpt3-5_backup? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Moved derek-thomas/falcon-v03-poe-FAR-gpt3-5 to derek-thomas/falcon-v03-poe-FAR-gpt3-5_backup\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to move the model from 'derek-thomas/falcon-v03-poe-FAR-falcon' to derek-thomas/falcon-v03-poe-FAR-falcon_backup? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Moved derek-thomas/falcon-v03-poe-FAR-falcon to derek-thomas/falcon-v03-poe-FAR-falcon_backup\n"
     ]
    },
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "Are you sure you want to move the model from 'derek-thomas/falcon-v03-poe-FA' to derek-thomas/falcon-v03-poe-FA_backup? (y/n):  y\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Moved derek-thomas/falcon-v03-poe-FA to derek-thomas/falcon-v03-poe-FA_backup\n"
     ]
    }
   ],
   "source": [
    "from huggingface_hub import move_repo\n",
    "\n",
    "for model in autotrain_models:\n",
    "    user, model_tag = model.split('/')\n",
    "    to = f\"{user}/{model_tag}_backup\"\n",
    "    confirm = input(f\"Are you sure you want to move the model from '{model}' to {to}? (y/n): \")\n",
    "    if confirm.lower() == 'y':\n",
    "        move_repo(from_id=model, to_id=to)\n",
    "        print(f\"Moved {model} to {to}\")\n",
    "    else:\n",
    "        print(f\"Skipped {model}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c2a2c864-2082-4be9-8e28-92fd01833e38",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}