{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from PIL import Image\n",
    "import requests\n",
    "import torch\n",
    "from torchvision import io\n",
    "from typing import Dict\n",
    "from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "29ac356cdb05492d8a2da9bceea03b37",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "config.json:   0%|          | 0.00/1.20k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Akhil PC\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\huggingface_hub\\file_download.py:157: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\Akhil PC\\.cache\\huggingface\\hub\\models--Qwen--Qwen2-VL-2B-Instruct. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
      "  warnings.warn(message)\n",
      "Unrecognized keys in `rope_scaling` for 'rope_type'='default': {'mrope_section'}\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3ca08388cd3a4bc58b5b3c84b57fcd7f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model.safetensors.index.json:   0%|          | 0.00/56.4k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7f667bff4c014fce85cb222f40508c78",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c4289d2bd8f0466586d20564fb8fef84",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model-00001-of-00002.safetensors:   0%|          | 0.00/3.99G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "47d67996509f431abb0f99bab97a03d6",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model-00002-of-00002.safetensors:   0%|          | 0.00/429M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "`Qwen2VLRotaryEmbedding` can now be fully parameterized by passing the model config through the `config` argument. All other arguments will be removed in v4.46\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d3e49e52f64147e2b5043c76d9a507e6",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5060e7d44d5b40fd8ca2d7e90542be21",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "generation_config.json:   0%|          | 0.00/272 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ac0500d6289442d88db22065e94c6df2",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "preprocessor_config.json:   0%|          | 0.00/347 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "99ff45911ba848f2bd3ccd3f57029641",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer_config.json:   0%|          | 0.00/4.19k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9d484f67779348d7b242a12de0505324",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "vocab.json:   0%|          | 0.00/2.78M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b0e6345cf4cd4b61b7d6b10ab7ae6f23",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "merges.txt:   0%|          | 0.00/1.67M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c108ffe24eab4d82a8aa8d5bda088bf7",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer.json:   0%|          | 0.00/7.03M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c9385ab1782f49fcb59fbe2aa73a81c5",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "chat_template.json:   0%|          | 0.00/1.05k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Load the model in half-precision on the available device(s)\n",
    "model = Qwen2VLForConditionalGeneration.from_pretrained(\"Qwen/Qwen2-VL-2B-Instruct\", device_map=\"cpu\", torch_dtype=torch.float16)\n",
    "processor = AutoProcessor.from_pretrained(\"Qwen/Qwen2-VL-2B-Instruct\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Image\n",
    "url = \"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg\"\n",
    "image = Image.open(requests.get(url, stream=True).raw)\n",
    "\n",
    "conversation = [\n",
    "    {\n",
    "        \"role\":\"user\",\n",
    "        \"content\":[\n",
    "            {\n",
    "                \"type\":\"image\",\n",
    "            },\n",
    "            {\n",
    "                \"type\":\"text\",\n",
    "                \"text\":\"Describe this image.\"\n",
    "            }\n",
    "        ]\n",
    "    }\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Preprocess the inputs\n",
    "text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "inputs = processor(text=[text_prompt], images=[image], padding=True, return_tensors=\"pt\")\n",
    "# inputs = inputs.to('cuda')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Inference: Generation of the output\n",
    "output_ids = model.generate(**inputs, max_new_tokens=128)\n",
    "generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)\n",
    "print(output_text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}