{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6e8eca77-926b-4c68-bacd-cd1e90114123",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "saved\n"
     ]
    }
   ],
   "source": [
    "from diffusers import FlowMatchEulerDiscreteScheduler\n",
    "import torch\n",
    "\n",
    "device=\"cuda\"\n",
    "dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32\n",
    "\n",
    "scheduler = FlowMatchEulerDiscreteScheduler()\n",
    "scheduler.init_noise_sigma = 1.\n",
    "\n",
    "scheduler.save_pretrained(\"scheduler\")\n",
    "print('saved')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f39feab5-1493-49fb-a527-7166c38fe6c7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AutoTokenizer, AutoModel\n",
    "import torch\n",
    "\n",
    "device=\"cuda\"\n",
    "dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32\n",
    "\n",
    "\n",
    "model=\"Qwen/Qwen3-1.7B\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(model)\n",
    "text_model = AutoModel.from_pretrained(model,torch_dtype=dtype).to(device).eval()\n",
    "\n",
    "print(text_model)\n",
    "print(tokenizer)\n",
    "tokenizer.save_pretrained(\"tokenizer\")\n",
    "text_model.save_pretrained(\"text_encoder\")\n",
    "print('saved')\n"
   ]
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}