{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ca60092b-a133-40d5-bce7-be261eb13ba3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/var/home/ngxson/jupyter/stories-15M\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
    "\n",
    "model_path = os.getcwd()\n",
    "print(model_path)\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_path, legacy=False)\n",
    "tokenizer.pad_token = tokenizer.eos_token\n",
    "model = AutoModelForCausalLM.from_pretrained(model_path, use_safetensors=True, local_files_only=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d8197b9a-9c94-4c14-9b89-5e16f129f71b",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
      "Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n",
      "The attention mask is not set and cannot be inferred from input because pad token is same as eos token.As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Look in thy glass was a little girl. She was only three years old and she was three years old. She was\n"
     ]
    }
   ],
   "source": [
    "inputs = tokenizer('Look in thy glass', return_tensors=\"pt\")\n",
    "outputs = model.generate(inputs['input_ids'], max_new_tokens=20)\n",
    "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "242b314c-d702-4cc1-862e-aaf59e986527",
   "metadata": {},
   "outputs": [],
   "source": [
    "from peft import PeftModel\n",
    "CHECKPOINT_PATH = 'moe_shakespeare15M/checkpoint-500'\n",
    "ft_model = PeftModel.from_pretrained(model, CHECKPOINT_PATH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a0abc08e-7e77-4efe-8e1b-465eff9672b3",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
      "Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Look in thy glass in love of the eye:\n",
      "That's when when the eye see thy on the sun'\n"
     ]
    }
   ],
   "source": [
    "outputs = ft_model.generate(inputs['input_ids'], max_new_tokens=20)\n",
    "print(tokenizer.decode(outputs[0], skip_special_tokens=True))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0733e354-6b16-4c8f-a7f9-6207d75feee1",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}