Upload llamaChatbot.ipynb

llamaChatbot.ipynb

@@ -0,0 +1,809 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "gpuType": "T4"
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "accelerator": "GPU",
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "cb82c295aa304cbab2c037caffc8d8d1": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_67367bae31384088aa07fc80aa68a081",
+              "IPY_MODEL_ed5621e9730641379c6b1c740c43ec1f",
+              "IPY_MODEL_4c31c17d684d434b88481c42404d5582"
+            ],
+            "layout": "IPY_MODEL_9e300fa0cd094325ac4ce2f1aa5cca8b"
+          }
+        },
+        "67367bae31384088aa07fc80aa68a081": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_2d58b05027644ae49d0d1c9b7a8c9f90",
+            "placeholder": "​",
+            "style": "IPY_MODEL_0e9108eb5ada489a93719771ba9a8903",
+            "value": "Loading checkpoint shards: 100%"
+          }
+        },
+        "ed5621e9730641379c6b1c740c43ec1f": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_8fea9e36d8a948c4a93e9613df9f9f48",
+            "max": 2,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_51e33ef50f6f48e1b6c7d3da4ade7819",
+            "value": 2
+          }
+        },
+        "4c31c17d684d434b88481c42404d5582": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_16ba2159038e4dafac854a238854cc93",
+            "placeholder": "​",
+            "style": "IPY_MODEL_b15a25c37e714190a8a3032ce16d8944",
+            "value": " 2/2 [00:59<00:00, 27.15s/it]"
+          }
+        },
+        "9e300fa0cd094325ac4ce2f1aa5cca8b": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "2d58b05027644ae49d0d1c9b7a8c9f90": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "0e9108eb5ada489a93719771ba9a8903": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "8fea9e36d8a948c4a93e9613df9f9f48": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "51e33ef50f6f48e1b6c7d3da4ade7819": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "16ba2159038e4dafac854a238854cc93": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "b15a25c37e714190a8a3032ce16d8944": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        }
+      }
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "qNGi-NeEQKyh"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install -q accelerate==0.21.0 peft==0.4.0 bitsandbytes==0.40.0 transformers==4.31.0 trl==0.4.7\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# import Libraries"
+      ],
+      "metadata": {
+        "id": "WauAa05-Qjvm"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import os\n",
+        "import torch\n",
+        "from datasets import load_dataset\n",
+        "from transformers import (\n",
+        "    AutoModelForCausalLM,\n",
+        "    AutoTokenizer,\n",
+        "    BitsAndBytesConfig,\n",
+        "    TrainingArguments,\n",
+        "    pipeline,\n",
+        "    logging,\n",
+        ")\n",
+        "from peft import LoraConfig\n",
+        "from trl import SFTTrainer"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "kHnoSTdZQchZ",
+        "outputId": "cb02da43-ae5a-4077-d4ae-73f3757a23f3"
+      },
+      "execution_count": 3,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "===================================BUG REPORT===================================\n",
+            "Welcome to bitsandbytes. For bug reports, please run\n",
+            "\n",
+            "python -m bitsandbytes\n",
+            "\n",
+            " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+            "================================================================================\n",
+            "bin /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cuda122.so\n",
+            "CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...\n",
+            "CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so\n",
+            "CUDA SETUP: Highest compute capability among GPUs detected: 7.5\n",
+            "CUDA SETUP: Detected CUDA version 122\n",
+            "CUDA SETUP: Loading binary /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cuda122.so...\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/lib64-nvidia did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\n",
+            "  warn(msg)\n",
+            "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/sys/fs/cgroup/memory.events /var/colab/cgroup/jupyter-children/memory.events')}\n",
+            "  warn(msg)\n",
+            "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('8013'), PosixPath('//172.28.0.1'), PosixPath('http')}\n",
+            "  warn(msg)\n",
+            "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//colab.research.google.com/tun/m/cc48301118ce562b961b3c22d803539adc1e0c19/gpu-t4-s-2m1xgbra9q2mp --tunnel_background_save_delay=10s --tunnel_periodic_background_save_frequency=30m0s --enable_output_coalescing=true --output_coalescing_required=true'), PosixPath('--logtostderr --listen_host=172.28.0.12 --target_host=172.28.0.12 --tunnel_background_save_url=https')}\n",
+            "  warn(msg)\n",
+            "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/datalab/web/pyright/typeshed-fallback/stdlib,/usr/local/lib/python3.10/dist-packages')}\n",
+            "  warn(msg)\n",
+            "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')}\n",
+            "  warn(msg)\n",
+            "/usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//ipykernel.pylab.backend_inline')}\n",
+            "  warn(msg)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Model from Hugging Face hub\n",
+        "base_model = \"NousResearch/Llama-2-7b-chat-hf\"\n",
+        "\n",
+        "# New instruction dataset\n",
+        "data = \"mlabonne/guanaco-llama2-1k\"\n",
+        "\n",
+        "# Fine-tuned model\n",
+        "new_model = \"llama\""
+      ],
+      "metadata": {
+        "id": "HK6v7rKIQc-N"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#Loading dataset, model, and tokenizer"
+      ],
+      "metadata": {
+        "id": "JwRCNdaCRCRg"
+      },
+      "execution_count": 6,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(data, split=\"train\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "RZxePacWQdAz",
+        "outputId": "8d4d4a5b-08f2-4ae2-b053-bf8fbf36d0a2"
+      },
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:88: UserWarning: \n",
+            "The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
+            "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
+            "You will be able to reuse this secret in all of your notebooks.\n",
+            "Please note that authentication is recommended but still optional to access public models or datasets.\n",
+            "  warnings.warn(\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#4-bit quantization configuration"
+      ],
+      "metadata": {
+        "id": "h1Jyci0XQ7fv"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "compute_dtype = getattr(torch, \"float16\")\n",
+        "\n",
+        "quant_config = BitsAndBytesConfig(\n",
+        "    load_in_4bit=True,\n",
+        "    bnb_4bit_quant_type=\"nf4\",\n",
+        "    bnb_4bit_compute_dtype=compute_dtype,\n",
+        "    bnb_4bit_use_double_quant=False,\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "CWdKioPXQdF2"
+      },
+      "execution_count": 8,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#Loading Llama 2 model\n",
+        "model = AutoModelForCausalLM.from_pretrained(\n",
+        "    base_model,\n",
+        "    quantization_config=quant_config,\n",
+        "    device_map={\"\": 0}\n",
+        ")\n",
+        "model.config.use_cache = False\n",
+        "model.config.pretraining_tp = 1"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 49,
+          "referenced_widgets": [
+            "cb82c295aa304cbab2c037caffc8d8d1",
+            "67367bae31384088aa07fc80aa68a081",
+            "ed5621e9730641379c6b1c740c43ec1f",
+            "4c31c17d684d434b88481c42404d5582",
+            "9e300fa0cd094325ac4ce2f1aa5cca8b",
+            "2d58b05027644ae49d0d1c9b7a8c9f90",
+            "0e9108eb5ada489a93719771ba9a8903",
+            "8fea9e36d8a948c4a93e9613df9f9f48",
+            "51e33ef50f6f48e1b6c7d3da4ade7819",
+            "16ba2159038e4dafac854a238854cc93",
+            "b15a25c37e714190a8a3032ce16d8944"
+          ]
+        },
+        "id": "yBKf8xyAQdIx",
+        "outputId": "90423d17-f99a-425f-9696-1309b370ce62"
+      },
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "cb82c295aa304cbab2c037caffc8d8d1"
+            }
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#Loading tokenizer"
+      ],
+      "metadata": {
+        "id": "JVgUFEy2Rffs"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)\n",
+        "tokenizer.pad_token = tokenizer.eos_token\n",
+        "tokenizer.padding_side = \"right\""
+      ],
+      "metadata": {
+        "id": "lPpE8LhQQdLd"
+      },
+      "execution_count": 10,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#PEFT parameters"
+      ],
+      "metadata": {
+        "id": "lUW2z345QdOI"
+      },
+      "execution_count": 11,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "peft_params = LoraConfig(\n",
+        "    lora_alpha=16,\n",
+        "    lora_dropout=0.1,\n",
+        "    r=64,\n",
+        "    bias=\"none\",\n",
+        "    task_type=\"CAUSAL_LM\",\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "jdspWkWcQdQq"
+      },
+      "execution_count": 12,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#Training parameters"
+      ],
+      "metadata": {
+        "id": "M-SkbgDRQdTq"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "training_params = TrainingArguments(\n",
+        "    output_dir=\"./results\",\n",
+        "    num_train_epochs=1,\n",
+        "    per_device_train_batch_size=4,\n",
+        "    gradient_accumulation_steps=1,\n",
+        "    optim=\"paged_adamw_32bit\",\n",
+        "    save_steps=25,\n",
+        "    logging_steps=25,\n",
+        "    learning_rate=2e-4,\n",
+        "    weight_decay=0.001,\n",
+        "    fp16=False,\n",
+        "    bf16=False,\n",
+        "    max_grad_norm=0.3,\n",
+        "    max_steps=-1,\n",
+        "    warmup_ratio=0.03,\n",
+        "    group_by_length=True,\n",
+        "    lr_scheduler_type=\"constant\",\n",
+        "    report_to=\"tensorboard\"\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "ROCMS2d4QdW9"
+      },
+      "execution_count": 13,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#Model fine-tuning"
+      ],
+      "metadata": {
+        "id": "mZdeHuytQdZ5"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "trainer = SFTTrainer(\n",
+        "    model=model,\n",
+        "    train_dataset=dataset,\n",
+        "    peft_config=peft_params,\n",
+        "    dataset_text_field=\"text\",\n",
+        "    max_seq_length=None,\n",
+        "    tokenizer=tokenizer,\n",
+        "    args=training_params,\n",
+        "    packing=False,\n",
+        ")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "o1vMJ7x_Qdb-",
+        "outputId": "aa0a32e3-c400-4c41-cb2f-9e91558cb339"
+      },
+      "execution_count": 14,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.\n",
+            "  warnings.warn(\n",
+            "/usr/local/lib/python3.10/dist-packages/trl/trainer/sft_trainer.py:159: UserWarning: You didn't pass a `max_seq_length` argument to the SFTTrainer, this will default to 1024\n",
+            "  warnings.warn(\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "trainer.model.save_pretrained(new_model)\n",
+        "trainer.tokenizer.save_pretrained(new_model)\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Zmoa7iLFUez7",
+        "outputId": "48c41a64-ad0f-475a-f186-f82d9df5a719"
+      },
+      "execution_count": 15,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "('llama/tokenizer_config.json',\n",
+              " 'llama/special_tokens_map.json',\n",
+              " 'llama/tokenizer.model',\n",
+              " 'llama/added_tokens.json',\n",
+              " 'llama/tokenizer.json')"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 15
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "logging.set_verbosity(logging.CRITICAL)\n",
+        "\n",
+        "prompt = input(\"Enter prompt here:-  \")\n",
+        "pipe = pipeline(task=\"text-generation\", model=model, tokenizer=tokenizer, max_length=200)\n",
+        "result = pipe(f\"<s>[INST] {prompt} [/INST]\")\n",
+        "print(result[0]['generated_text'])"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "UiSr45NDQdrx",
+        "outputId": "6c610f76-cd4f-4467-e1a3-a1a7cbe7de85"
+      },
+      "execution_count": 16,
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Enter prompt here:-  sharad pawar\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py:1270: UserWarning: You have modified the pretrained model configuration to control generation. This is a deprecated strategy to control generation and will be removed soon, in a future version. Please use a generation configuration file (see https://huggingface.co/docs/transformers/main_classes/text_generation )\n",
+            "  warnings.warn(\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "<s>[INST] sharad pawar [/INST]  Sharad Pawar is a prominent Indian politician and the current President of the Nationalist Congress Party (NCP). Here are some key facts about him:\n",
+            " Unterscheidung:\n",
+            "\n",
+            "1. Early life and education: Sharad Pawar was born on December 12, 1940, in the village of Baramati in the state of Maharashtra, India. He completed his primary education in Baramati and later moved to Mumbai to pursue his higher education.\n",
+            "2. Political career: Pawar began his political career in the 1960s as a member of the Janata Party. He later joined the Indian National Congress and became a member of the Maharashtra Legislative Assembly in 1978. He served as the Chief Minister of Maharashtra from 1978 to \n"
+          ]
+        }
+      ]
+    }
+  ]
+}