{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from huggingface_hub import login\n",
    "from dotenv import load_dotenv\n",
    "import os\n",
    "load_dotenv()\n",
    "\n",
    "# Login to Hugging Face Hub\n",
    "login(token=os.getenv(\"HUGGINGFACE_TOKEN\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d00ec085003e409d906784abc1f89dc1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "config.json:   0%|          | 0.00/838 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "f:\\TADBot\\.venv\\Lib\\site-packages\\huggingface_hub\\file_download.py:139: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in F:\\TADBot\\Gemma2_2B\\.cache\\models--google--gemma-2-2b-it. 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 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"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bdee67c51d7547a48e45f17db7fb3734",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model.safetensors.index.json:   0%|          | 0.00/24.2k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ad86eff32cc1447486e69c5f5f90e4a4",
       "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": "78cab016a2d54731a94ef45e85d65ddd",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model-00001-of-00002.safetensors:   0%|          | 0.00/4.99G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "52b50ff81d0d481ab475878606935162",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model-00002-of-00002.safetensors:   0%|          | 0.00/241M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "7dfed61b7e0a4338aee7ad14df4d85ca",
       "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": "9ac1e6a0b72a44d3a8a648bce2138c3d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "generation_config.json:   0%|          | 0.00/187 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f0129c204a454f22968aebe59b75ea1a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer_config.json:   0%|          | 0.00/47.0k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ca55b303b11347cbbf5970327d2d8a82",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer.model:   0%|          | 0.00/4.24M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "33601521ca8544e7a98c88506257dd20",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer.json:   0%|          | 0.00/17.5M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f353232bbf6b4da3ac62e02fa7f58990",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "special_tokens_map.json:   0%|          | 0.00/636 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
    "model_name = \"google/gemma-2-2b-it\"\n",
    "model = AutoModelForCausalLM.from_pretrained(model_name, device_map=\"auto\", cache_dir=\".cache/\")\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_name, cache_dir=\".cache/\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gemma2ForCausalLM(\n",
      "  (model): Gemma2Model(\n",
      "    (embed_tokens): Embedding(256000, 2304, padding_idx=0)\n",
      "    (layers): ModuleList(\n",
      "      (0-25): 26 x Gemma2DecoderLayer(\n",
      "        (self_attn): Gemma2Attention(\n",
      "          (q_proj): Linear(in_features=2304, out_features=2048, bias=False)\n",
      "          (k_proj): Linear(in_features=2304, out_features=1024, bias=False)\n",
      "          (v_proj): Linear(in_features=2304, out_features=1024, bias=False)\n",
      "          (o_proj): Linear(in_features=2048, out_features=2304, bias=False)\n",
      "          (rotary_emb): Gemma2RotaryEmbedding()\n",
      "        )\n",
      "        (mlp): Gemma2MLP(\n",
      "          (gate_proj): Linear(in_features=2304, out_features=9216, bias=False)\n",
      "          (up_proj): Linear(in_features=2304, out_features=9216, bias=False)\n",
      "          (down_proj): Linear(in_features=9216, out_features=2304, bias=False)\n",
      "          (act_fn): PytorchGELUTanh()\n",
      "        )\n",
      "        (input_layernorm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "        (pre_feedforward_layernorm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "        (post_feedforward_layernorm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "        (post_attention_layernorm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "      )\n",
      "    )\n",
      "    (norm): Gemma2RMSNorm((2304,), eps=1e-06)\n",
      "  )\n",
      "  (lm_head): Linear(in_features=2304, out_features=256000, bias=False)\n",
      ")\n"
     ]
    }
   ],
   "source": [
    "print(model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<bos>What should I do on a trip to Europe?\n",
      "\n",
      "That's a great question!  To give you the best advice, I need a little more information. Tell me about:\n",
      "\n",
      "**1. Your Interests:** \n",
      "   * What kind of things do you enjoy doing? (History, art, food, nightlife, nature, adventure, relaxation, etc.)\n",
      "   * Are there any specific places or activities you've always wanted to experience?\n",
      "\n",
      "**2. Your Travel Style:**\n",
      "   * Do you prefer to travel on your own, with a partner, or with a group?\n",
      "   * Do you like to plan everything in advance or be more spontaneous?\n",
      "   * What's your budget like?\n",
      "\n",
      "**3. Your Trip Details:**\n",
      "   * How long will you be traveling for?\n",
      "   * What time of year are you planning to go?\n",
      "   * Do you have any specific destinations in mind?\n",
      "\n",
      "Once I have this information, I can give you personalized recommendations for your European adventure! \n",
      "<end_of_turn>\n",
      "CPU times: total: 7.23 s\n",
      "Wall time: 7.56 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "input_text = \"What should I do on a trip to Europe?\"\n",
    "\n",
    "input_ids = tokenizer(input_text, return_tensors=\"pt\").to(\"cuda\")\n",
    "outputs = model.generate(**input_ids, max_length=2048)\n",
    "print(tokenizer.decode(outputs[0]))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}