{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bert.modeling_bert.BertModel'>\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoModel\n",
    "\n",
    "bert_model = AutoModel.from_pretrained('bert-base-cased')\n",
    "print(type(bert_model))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.gpt2.modeling_gpt2.GPT2Model'>\n"
     ]
    }
   ],
   "source": [
    "gpt_model = AutoModel.from_pretrained('gpt2')\n",
    "print(type(gpt_model))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bart.modeling_bart.BartModel'>\n"
     ]
    }
   ],
   "source": [
    "bart_model = AutoModel.from_pretrained('facebook/bart-base')\n",
    "print(type(bart_model))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bert.configuration_bert.BertConfig'>\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoConfig\n",
    "\n",
    "bert_config = AutoConfig.from_pretrained('bert-base-cased')\n",
    "print(type(bert_config))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertConfig {\n",
      "  \"_name_or_path\": \"bert-base-cased\",\n",
      "  \"architectures\": [\n",
      "    \"BertForMaskedLM\"\n",
      "  ],\n",
      "  \"attention_probs_dropout_prob\": 0.1,\n",
      "  \"classifier_dropout\": null,\n",
      "  \"gradient_checkpointing\": false,\n",
      "  \"hidden_act\": \"gelu\",\n",
      "  \"hidden_dropout_prob\": 0.1,\n",
      "  \"hidden_size\": 768,\n",
      "  \"initializer_range\": 0.02,\n",
      "  \"intermediate_size\": 3072,\n",
      "  \"layer_norm_eps\": 1e-12,\n",
      "  \"max_position_embeddings\": 512,\n",
      "  \"model_type\": \"bert\",\n",
      "  \"num_attention_heads\": 12,\n",
      "  \"num_hidden_layers\": 12,\n",
      "  \"pad_token_id\": 0,\n",
      "  \"position_embedding_type\": \"absolute\",\n",
      "  \"transformers_version\": \"4.34.1\",\n",
      "  \"type_vocab_size\": 2,\n",
      "  \"use_cache\": true,\n",
      "  \"vocab_size\": 28996\n",
      "}\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(bert_config)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bert.configuration_bert.BertConfig'>\n",
      "<class 'transformers.models.bert.configuration_bert.BertConfig'>\n"
     ]
    }
   ],
   "source": [
    "from transformers import BertConfig\n",
    "\n",
    "bert_config = BertConfig.from_pretrained('bert-base-cased')\n",
    "print(type(bert_config))\n",
    "\n",
    "from transformers import AutoConfig\n",
    "\n",
    "bert_config = AutoConfig.from_pretrained('bert-base-cased')\n",
    "print(type(bert_config))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertConfig {\n",
      "  \"_name_or_path\": \"bert-base-cased\",\n",
      "  \"architectures\": [\n",
      "    \"BertForMaskedLM\"\n",
      "  ],\n",
      "  \"attention_probs_dropout_prob\": 0.1,\n",
      "  \"classifier_dropout\": null,\n",
      "  \"gradient_checkpointing\": false,\n",
      "  \"hidden_act\": \"gelu\",\n",
      "  \"hidden_dropout_prob\": 0.1,\n",
      "  \"hidden_size\": 768,\n",
      "  \"initializer_range\": 0.02,\n",
      "  \"intermediate_size\": 3072,\n",
      "  \"layer_norm_eps\": 1e-12,\n",
      "  \"max_position_embeddings\": 512,\n",
      "  \"model_type\": \"bert\",\n",
      "  \"num_attention_heads\": 12,\n",
      "  \"num_hidden_layers\": 12,\n",
      "  \"pad_token_id\": 0,\n",
      "  \"position_embedding_type\": \"absolute\",\n",
      "  \"transformers_version\": \"4.34.1\",\n",
      "  \"type_vocab_size\": 2,\n",
      "  \"use_cache\": true,\n",
      "  \"vocab_size\": 28996\n",
      "}\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(bert_config)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertModel(\n",
      "  (embeddings): BertEmbeddings(\n",
      "    (word_embeddings): Embedding(28996, 768, padding_idx=0)\n",
      "    (position_embeddings): Embedding(512, 768)\n",
      "    (token_type_embeddings): Embedding(2, 768)\n",
      "    (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "    (dropout): Dropout(p=0.1, inplace=False)\n",
      "  )\n",
      "  (encoder): BertEncoder(\n",
      "    (layer): ModuleList(\n",
      "      (0-11): 12 x BertLayer(\n",
      "        (attention): BertAttention(\n",
      "          (self): BertSelfAttention(\n",
      "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "          (output): BertSelfOutput(\n",
      "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "        )\n",
      "        (intermediate): BertIntermediate(\n",
      "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
      "          (intermediate_act_fn): GELUActivation()\n",
      "        )\n",
      "        (output): BertOutput(\n",
      "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
      "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "          (dropout): Dropout(p=0.1, inplace=False)\n",
      "        )\n",
      "      )\n",
      "    )\n",
      "  )\n",
      "  (pooler): BertPooler(\n",
      "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "    (activation): Tanh()\n",
      "  )\n",
      ")\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoModel\n",
    "\n",
    "bert_model = AutoModel.from_pretrained('bert-base-cased')\n",
    "print(bert_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertModel(\n",
      "  (embeddings): BertEmbeddings(\n",
      "    (word_embeddings): Embedding(28996, 768, padding_idx=0)\n",
      "    (position_embeddings): Embedding(512, 768)\n",
      "    (token_type_embeddings): Embedding(2, 768)\n",
      "    (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "    (dropout): Dropout(p=0.1, inplace=False)\n",
      "  )\n",
      "  (encoder): BertEncoder(\n",
      "    (layer): ModuleList(\n",
      "      (0-11): 12 x BertLayer(\n",
      "        (attention): BertAttention(\n",
      "          (self): BertSelfAttention(\n",
      "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "          (output): BertSelfOutput(\n",
      "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "        )\n",
      "        (intermediate): BertIntermediate(\n",
      "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
      "          (intermediate_act_fn): GELUActivation()\n",
      "        )\n",
      "        (output): BertOutput(\n",
      "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
      "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "          (dropout): Dropout(p=0.1, inplace=False)\n",
      "        )\n",
      "      )\n",
      "    )\n",
      "  )\n",
      "  (pooler): BertPooler(\n",
      "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "    (activation): Tanh()\n",
      "  )\n",
      ")\n",
      "BertModel(\n",
      "  (embeddings): BertEmbeddings(\n",
      "    (word_embeddings): Embedding(28996, 768, padding_idx=0)\n",
      "    (position_embeddings): Embedding(512, 768)\n",
      "    (token_type_embeddings): Embedding(2, 768)\n",
      "    (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "    (dropout): Dropout(p=0.1, inplace=False)\n",
      "  )\n",
      "  (encoder): BertEncoder(\n",
      "    (layer): ModuleList(\n",
      "      (0-7): 8 x BertLayer(\n",
      "        (attention): BertAttention(\n",
      "          (self): BertSelfAttention(\n",
      "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "          (output): BertSelfOutput(\n",
      "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "        )\n",
      "        (intermediate): BertIntermediate(\n",
      "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
      "          (intermediate_act_fn): GELUActivation()\n",
      "        )\n",
      "        (output): BertOutput(\n",
      "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
      "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "          (dropout): Dropout(p=0.1, inplace=False)\n",
      "        )\n",
      "      )\n",
      "    )\n",
      "  )\n",
      "  (pooler): BertPooler(\n",
      "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "    (activation): Tanh()\n",
      "  )\n",
      ")\n"
     ]
    }
   ],
   "source": [
    "from transformers import BertConfig, BertModel\n",
    "\n",
    "bert_config = BertConfig.from_pretrained('bert-base-cased')\n",
    "bert_model = BertModel(bert_config)\n",
    "print(bert_model)\n",
    "\n",
    "bert_config = BertConfig.from_pretrained('bert-base-cased', num_hidden_layers=8)\n",
    "bert_model = BertModel(bert_config)\n",
    "print(bert_model)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertConfig {\n",
      "  \"architectures\": [\n",
      "    \"BertForMaskedLM\"\n",
      "  ],\n",
      "  \"attention_probs_dropout_prob\": 0.1,\n",
      "  \"classifier_dropout\": null,\n",
      "  \"gradient_checkpointing\": false,\n",
      "  \"hidden_act\": \"gelu\",\n",
      "  \"hidden_dropout_prob\": 0.1,\n",
      "  \"hidden_size\": 768,\n",
      "  \"initializer_range\": 0.02,\n",
      "  \"intermediate_size\": 3072,\n",
      "  \"layer_norm_eps\": 1e-12,\n",
      "  \"max_position_embeddings\": 512,\n",
      "  \"model_type\": \"bert\",\n",
      "  \"num_attention_heads\": 12,\n",
      "  \"num_hidden_layers\": 12,\n",
      "  \"pad_token_id\": 0,\n",
      "  \"position_embedding_type\": \"absolute\",\n",
      "  \"transformers_version\": \"4.34.1\",\n",
      "  \"type_vocab_size\": 2,\n",
      "  \"use_cache\": true,\n",
      "  \"vocab_size\": 28996\n",
      "}\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from transformers import BertConfig, BertModel\n",
    "bert_config_original = BertConfig.from_pretrained('bert-base-cased')\n",
    "print(bert_config_original)\n",
    "# bert_config = BertConfig.from_pretrained('bert-base-cased', num_hidden_layers=8)\n",
    "# bert_model = BertModel(bert_config)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertConfig {\n",
      "  \"_name_or_path\": \"bert-base-cased\",\n",
      "  \"architectures\": [\n",
      "    \"BertForMaskedLM\"\n",
      "  ],\n",
      "  \"attention_probs_dropout_prob\": 0.1,\n",
      "  \"classifier_dropout\": null,\n",
      "  \"gradient_checkpointing\": false,\n",
      "  \"hidden_act\": \"gelu\",\n",
      "  \"hidden_dropout_prob\": 0.1,\n",
      "  \"hidden_size\": 768,\n",
      "  \"initializer_range\": 0.02,\n",
      "  \"intermediate_size\": 3072,\n",
      "  \"layer_norm_eps\": 1e-12,\n",
      "  \"max_position_embeddings\": 512,\n",
      "  \"model_type\": \"bert\",\n",
      "  \"num_attention_heads\": 12,\n",
      "  \"num_hidden_layers\": 2,\n",
      "  \"pad_token_id\": 0,\n",
      "  \"position_embedding_type\": \"absolute\",\n",
      "  \"transformers_version\": \"4.34.1\",\n",
      "  \"type_vocab_size\": 2,\n",
      "  \"use_cache\": true,\n",
      "  \"vocab_size\": 100\n",
      "}\n",
      "\n"
     ]
    }
   ],
   "source": [
    "bert_config_new = AutoConfig.from_pretrained('bert-base-cased', \n",
    "                                             num_hidden_layers=2,\n",
    "                                             vocab_size=100,\n",
    "                                             )\n",
    "print(bert_config_new)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertModel(\n",
      "  (embeddings): BertEmbeddings(\n",
      "    (word_embeddings): Embedding(100, 768, padding_idx=0)\n",
      "    (position_embeddings): Embedding(512, 768)\n",
      "    (token_type_embeddings): Embedding(2, 768)\n",
      "    (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "    (dropout): Dropout(p=0.1, inplace=False)\n",
      "  )\n",
      "  (encoder): BertEncoder(\n",
      "    (layer): ModuleList(\n",
      "      (0-1): 2 x BertLayer(\n",
      "        (attention): BertAttention(\n",
      "          (self): BertSelfAttention(\n",
      "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "          (output): BertSelfOutput(\n",
      "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "        )\n",
      "        (intermediate): BertIntermediate(\n",
      "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
      "          (intermediate_act_fn): GELUActivation()\n",
      "        )\n",
      "        (output): BertOutput(\n",
      "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
      "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "          (dropout): Dropout(p=0.1, inplace=False)\n",
      "        )\n",
      "      )\n",
      "    )\n",
      "  )\n",
      "  (pooler): BertPooler(\n",
      "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "    (activation): Tanh()\n",
      "  )\n",
      ")\n"
     ]
    }
   ],
   "source": [
    "bert_model_new = BertModel(bert_config_new)\n",
    "print(bert_model_new)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "bert_model_new.save_pretrained('pew_bert_ye')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertModel(\n",
      "  (embeddings): BertEmbeddings(\n",
      "    (word_embeddings): Embedding(100, 768, padding_idx=0)\n",
      "    (position_embeddings): Embedding(512, 768)\n",
      "    (token_type_embeddings): Embedding(2, 768)\n",
      "    (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "    (dropout): Dropout(p=0.1, inplace=False)\n",
      "  )\n",
      "  (encoder): BertEncoder(\n",
      "    (layer): ModuleList(\n",
      "      (0-1): 2 x BertLayer(\n",
      "        (attention): BertAttention(\n",
      "          (self): BertSelfAttention(\n",
      "            (query): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (key): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (value): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "          (output): BertSelfOutput(\n",
      "            (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "            (dropout): Dropout(p=0.1, inplace=False)\n",
      "          )\n",
      "        )\n",
      "        (intermediate): BertIntermediate(\n",
      "          (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
      "          (intermediate_act_fn): GELUActivation()\n",
      "        )\n",
      "        (output): BertOutput(\n",
      "          (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
      "          (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
      "          (dropout): Dropout(p=0.1, inplace=False)\n",
      "        )\n",
      "      )\n",
      "    )\n",
      "  )\n",
      "  (pooler): BertPooler(\n",
      "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
      "    (activation): Tanh()\n",
      "  )\n",
      ")\n"
     ]
    }
   ],
   "source": [
    "bert_model_new = BertModel.from_pretrained('pew_bert_ye')\n",
    "print(bert_model_new)"
   ]
  },
  {
   "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}