{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b3b92bc7-d105-405f-970d-804d298b9976",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting accelerate\n",
      "  Downloading accelerate-0.27.2-py3-none-any.whl.metadata (18 kB)\n",
      "Collecting transformers\n",
      "  Downloading transformers-4.37.2-py3-none-any.whl.metadata (129 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.4/129.4 kB\u001b[0m \u001b[31m65.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting einops\n",
      "  Downloading einops-0.7.0-py3-none-any.whl.metadata (13 kB)\n",
      "Collecting datasets\n",
      "  Downloading datasets-2.17.1-py3-none-any.whl.metadata (20 kB)\n",
      "Collecting peft\n",
      "  Downloading peft-0.8.2-py3-none-any.whl.metadata (25 kB)\n",
      "Collecting bitsandbytes\n",
      "  Downloading bitsandbytes-0.42.0-py3-none-any.whl.metadata (9.9 kB)\n",
      "Collecting torch\n",
      "  Downloading torch-2.2.0-cp311-cp311-manylinux1_x86_64.whl.metadata (25 kB)\n",
      "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/site-packages (from accelerate) (1.26.4)\n",
      "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/site-packages (from accelerate) (23.2)\n",
      "Requirement already satisfied: psutil in /usr/local/lib/python3.11/site-packages (from accelerate) (5.9.8)\n",
      "Requirement already satisfied: pyyaml in /usr/local/lib/python3.11/site-packages (from accelerate) (6.0.1)\n",
      "Collecting huggingface-hub (from accelerate)\n",
      "  Downloading huggingface_hub-0.20.3-py3-none-any.whl.metadata (12 kB)\n",
      "Collecting safetensors>=0.3.1 (from accelerate)\n",
      "  Downloading safetensors-0.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n",
      "Collecting filelock (from transformers)\n",
      "  Downloading filelock-3.13.1-py3-none-any.whl.metadata (2.8 kB)\n",
      "Collecting regex!=2019.12.17 (from transformers)\n",
      "  Downloading regex-2023.12.25-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m450.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: requests in /usr/local/lib/python3.11/site-packages (from transformers) (2.31.0)\n",
      "Collecting tokenizers<0.19,>=0.14 (from transformers)\n",
      "  Downloading tokenizers-0.15.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
      "Collecting tqdm>=4.27 (from transformers)\n",
      "  Downloading tqdm-4.66.2-py3-none-any.whl.metadata (57 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.6/57.6 kB\u001b[0m \u001b[31m130.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hCollecting pyarrow>=12.0.0 (from datasets)\n",
      "  Downloading pyarrow-15.0.0-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (3.0 kB)\n",
      "Collecting pyarrow-hotfix (from datasets)\n",
      "  Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n",
      "Collecting dill<0.3.9,>=0.3.0 (from datasets)\n",
      "  Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n",
      "Collecting pandas (from datasets)\n",
      "  Downloading pandas-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (19 kB)\n",
      "Collecting xxhash (from datasets)\n",
      "  Downloading xxhash-3.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
      "Collecting multiprocess (from datasets)\n",
      "  Downloading multiprocess-0.70.16-py311-none-any.whl.metadata (7.2 kB)\n",
      "Collecting fsspec<=2023.10.0,>=2023.1.0 (from fsspec[http]<=2023.10.0,>=2023.1.0->datasets)\n",
      "  Downloading fsspec-2023.10.0-py3-none-any.whl.metadata (6.8 kB)\n",
      "Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/site-packages (from datasets) (3.8.3)\n",
      "Collecting scipy (from bitsandbytes)\n",
      "  Downloading scipy-1.12.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)\n",
      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.4/60.4 kB\u001b[0m \u001b[31m433.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hRequirement already satisfied: typing-extensions>=4.8.0 in /usr/local/lib/python3.11/site-packages (from torch) (4.9.0)\n",
      "Collecting sympy (from torch)\n",
      "  Downloading sympy-1.12-py3-none-any.whl.metadata (12 kB)\n",
      "Collecting networkx (from torch)\n",
      "  Downloading networkx-3.2.1-py3-none-any.whl.metadata (5.2 kB)\n",
      "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/site-packages (from torch) (3.1.3)\n",
      "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch)\n",
      "  Downloading 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)\n",
      "  Downloading 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)\n",
      "  Downloading 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)\n",
      "  Downloading 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)\n",
      "  Downloading 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)\n",
      "  Downloading 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)\n",
      "  Downloading 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)\n",
      "  Downloading 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)\n",
      "  Downloading 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)\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)\n",
      "  Downloading nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl.metadata (1.7 kB)\n",
      "Collecting triton==2.2.0 (from torch)\n",
      "  Downloading triton-2.2.0-cp311-cp311-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)\n",
      "  Downloading nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux1_x86_64.whl.metadata (1.5 kB)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (23.2.0)\n",
      "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (2.1.1)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (6.0.5)\n",
      "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (4.0.3)\n",
      "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.9.4)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.4.1)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/site-packages (from aiohttp->datasets) (1.3.1)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (3.6)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (2.2.0)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/site-packages (from requests->transformers) (2024.2.2)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/site-packages (from jinja2->torch) (2.1.5)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/site-packages (from pandas->datasets) (2.8.2)\n",
      "Collecting pytz>=2020.1 (from pandas->datasets)\n",
      "  Downloading pytz-2024.1-py2.py3-none-any.whl.metadata (22 kB)\n",
      "Collecting tzdata>=2022.7 (from pandas->datasets)\n",
      "  Downloading tzdata-2024.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
      "Collecting mpmath>=0.19 (from sympy->torch)\n",
      "  Downloading mpmath-1.3.0-py3-none-any.whl.metadata (8.6 kB)\n",
      "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/site-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n",
      "Downloading accelerate-0.27.2-py3-none-any.whl (279 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m280.0/280.0 kB\u001b[0m \u001b[31m147.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading transformers-4.37.2-py3-none-any.whl (8.4 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.4/8.4 MB\u001b[0m \u001b[31m311.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading einops-0.7.0-py3-none-any.whl (44 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m441.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading datasets-2.17.1-py3-none-any.whl (536 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.7/536.7 kB\u001b[0m \u001b[31m504.8 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[31m438.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading bitsandbytes-0.42.0-py3-none-any.whl (105.0 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.0/105.0 MB\u001b[0m \u001b[31m274.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hDownloading torch-2.2.0-cp311-cp311-manylinux1_x86_64.whl (755.5 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m755.5/755.5 MB\u001b[0m \u001b[31m235.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m255.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m220.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m200.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m566.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
      "\u001b[2K   \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━━━━━\u001b[0m \u001b[32m561.0/731.7 MB\u001b[0m \u001b[31m218.7 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m"
     ]
    }
   ],
   "source": [
    "!pip install accelerate transformers einops datasets peft bitsandbytes torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "46a53303-b585-4b02-956f-4af173410e25",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from datasets import load_dataset, Dataset\n",
    "from transformers import AutoModelForCausalLM, AutoTokenizer, TrainingArguments, Trainer, DataCollatorForLanguageModeling, BitsAndBytesConfig\n",
    "from peft import LoraConfig, get_peft_model\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ffa3ee11-3929-4032-8758-322cda3a912e",
   "metadata": {},
   "outputs": [],
   "source": [
    "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-2\", trust_remote_code=True)\n",
    "tokenizer.pad_token = tokenizer.eos_token"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b17096e6-c633-4d88-8cfc-fb738c1e4ca0",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "bnb_config = BitsAndBytesConfig(\n",
    "    load_in_4bit=True,\n",
    "    bnb_4bit_use_double_quant=True,\n",
    "    bnb_4bit_quant_type=\"nf4\",\n",
    "    bnb_4bit_compute_dtype=torch.float16\n",
    ")\n",
    "\n",
    "model = AutoModelForCausalLM.from_pretrained(\n",
    "    \"microsoft/phi-2\",\n",
    "    device_map={\"\":0},\n",
    "    trust_remote_code=True,\n",
    "    quantization_config=bnb_config\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e15aa794-e17c-4b09-a64a-c60377259218",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "18d5599f-992d-4d8e-a90c-4d43774be473",
   "metadata": {},
   "outputs": [],
   "source": [
    "# config = LoraConfig(\n",
    "#     r=16,\n",
    "#     lora_alpha=16,\n",
    "#     #target_modules=[\"q_proj\",\"k_proj\",\"v_proj\"],\n",
    "#     lora_dropout=0.05,\n",
    "#     bias=\"none\",\n",
    "#     task_type=\"CAUSAL_LM\"\n",
    "# )\n",
    "\n",
    "# model = get_peft_model(model, config)\n",
    "# model.print_trainable_parameters()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "baeee903-3dce-48b2-93c3-7a697d8c6daf",
   "metadata": {},
   "outputs": [],
   "source": [
    "def tokenize(sample):\n",
    "    model_inps =  tokenizer(sample[\"text\"], padding=True, truncation=True, max_length=512)\n",
    "    return model_inps"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "28a9b24a-a822-4fcb-96b3-d77b7ea30a5f",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install scikit-learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1ee7fd2a-38e4-4f23-a978-0bdeeda64d8b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "dataset_name='data.csv'\n",
    "df = pd.read_csv(dataset_name)\n",
    "#train, test = train_test_split(df, test_size=0.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e84c29e2-843e-42c2-8c0f-324d392e671c",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_df = df\n",
    "data_df[\"text\"] = data_df[[\"user\", \"assistant\"]].apply(lambda x: \"question: \" + str(x[\"user\"]) + \" answer: \" + str(x[\"assistant\"]), axis=1)\n",
    "data = Dataset.from_pandas(data_df)\n",
    "tokenized_data = data.map(tokenize, batched=True, desc=\"Tokenizing data\", remove_columns=data.column_names)\n",
    "tokenized_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ac968254-5338-49df-950d-222b82647407",
   "metadata": {},
   "outputs": [],
   "source": [
    "training_arguments = TrainingArguments(\n",
    "        output_dir=\".\",\n",
    "        per_device_train_batch_size=4,\n",
    "        gradient_accumulation_steps=1,\n",
    "        learning_rate=2e-4,\n",
    "        lr_scheduler_type=\"cosine\",\n",
    "        save_strategy=\"epoch\",\n",
    "        logging_steps=50,\n",
    "        max_steps=10000,\n",
    "        num_train_epochs=3,\n",
    "        push_to_hub=True\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "729df2d0-0890-4ac4-adf3-c167a6e9669d",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install huggingface_hub"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "525f81a4-eb92-466e-bb9c-cd63122231ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "pip install --upgrade jupyterlab jupyterlab-git"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "05d58512-a9e2-4319-88bf-9331c6a0584c",
   "metadata": {},
   "outputs": [],
   "source": [
    "from huggingface_hub import interpreter_login\n",
    "interpreter_login()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bcb01d1b-9a48-46fe-b020-51a4d61df532",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    " !pip install torch==2.1.0 pytorch-lightning==1.9.4 accelerate==0.21.0 tokenizers==0.13.3 transformers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d76b4865-df75-4793-b8b9-d97523445945",
   "metadata": {},
   "outputs": [],
   "source": [
    "model.enable_input_require_grads()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3bf553b6-b26c-49c3-9407-74c8d53a395e",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "trainer = Trainer(\n",
    "    model=model,\n",
    "    train_dataset=tokenized_data,\n",
    "    args=training_arguments,\n",
    "    data_collator=DataCollatorForLanguageModeling(tokenizer, mlm=False)\n",
    ")\n",
    "trainer.train()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "263cc15e-8e9d-4bd8-9708-ec1638bc1165",
   "metadata": {},
   "outputs": [],
   "source": [
    "from peft import PeftModel\n",
    "from transformers import AutoModelForCausalLM\n",
    "import torch\n",
    "model = AutoModelForCausalLM.from_pretrained(\"microsoft/phi-2\", trust_remote_code=True, torch_dtype=torch.float32)\n",
    "# peft_model = PeftModel.from_pretrained(model, \"aissatoubalde/lab\", from_transformers=True)\n",
    "# model = peft_model.merge_and_unload()\n",
    "# model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8eef4f4f-52da-4ba9-8a22-2b7874420562",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "model.push_to_hub('aissatoubalde/lab')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fa43c8e1-945e-41ef-b2f6-e90db1f50140",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}