Heisenberg08/Text2SQL
1
1{2 "cells": [3 {4 "cell_type": "code",5 "execution_count": 1,6 "metadata": {},7 "outputs": [],8 "source": [9 "import torch\n",10 "import transformers\n",11 "from transformers import AutoTokenizer, AutoModelWithLMHead\n"12 ]13 },14 {15 "cell_type": "code",16 "execution_count": 2,17 "metadata": {},18 "outputs": [],19 "source": [20 "tokenizer = AutoTokenizer.from_pretrained(\"EleutherAI/gpt-neo-125M\")\n"21 ]22 },23 {24 "cell_type": "code",25 "execution_count": 3,26 "metadata": {},27 "outputs": [28 {29 "name": "stderr",30 "output_type": "stream",31 "text": [32 "c:\\Users\\ADMIN\\textifyai\\lib\\site-packages\\transformers\\models\\auto\\modeling_auto.py:664: FutureWarning: The class `AutoModelWithLMHead` is deprecated and will be removed in a future version. Please use `AutoModelForCausalLM` for causal language models, `AutoModelForMaskedLM` for masked language models and `AutoModelForSeq2SeqLM` for encoder-decoder models.\n",33 " FutureWarning,\n"34 ]35 }36 ],37 "source": [38 "# model= AutoModelWithLMHead.from_pretrained(\"EleutherAI/gpt-neo-125M\")\n"39 ]40 },41 {42 "cell_type": "code",43 "execution_count": 4,44 "metadata": {},45 "outputs": [46 {47 "ename": "AttributeError",48 "evalue": "Can't get attribute 'NewGELUActivation' on <module 'transformers.activations' from 'c:\\\\Users\\\\ADMIN\\\\textifyai\\\\lib\\\\site-packages\\\\transformers\\\\activations.py'>",49 "output_type": "error",50 "traceback": [51 "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",52 "\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",53 "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_9168/1093822913.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Gpt_neo_Epoch_10_Loss_031_data_5000.pth\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mmap_location\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'cpu'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",54 "\u001b[1;32mc:\\Users\\ADMIN\\textifyai\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36mload\u001b[1;34m(f, map_location, pickle_module, **pickle_load_args)\u001b[0m\n\u001b[0;32m 605\u001b[0m \u001b[0mopened_file\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mseek\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0morig_position\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 606\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mjit\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mopened_file\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 607\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0m_load\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mopened_zipfile\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmap_location\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_module\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mpickle_load_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 608\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0m_legacy_load\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mopened_file\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmap_location\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpickle_module\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mpickle_load_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 609\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",55 "\u001b[1;32mc:\\Users\\ADMIN\\textifyai\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36m_load\u001b[1;34m(zip_file, map_location, pickle_module, pickle_file, **pickle_load_args)\u001b[0m\n\u001b[0;32m 880\u001b[0m \u001b[0munpickler\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mUnpicklerWrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_file\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mpickle_load_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 881\u001b[0m \u001b[0munpickler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpersistent_load\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpersistent_load\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 882\u001b[1;33m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0munpickler\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 883\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 884\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_utils\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_validate_loaded_sparse_tensors\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",56 "\u001b[1;32mc:\\Users\\ADMIN\\textifyai\\lib\\site-packages\\torch\\serialization.py\u001b[0m in \u001b[0;36mfind_class\u001b[1;34m(self, mod_name, name)\u001b[0m\n\u001b[0;32m 873\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mfind_class\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmod_name\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 874\u001b[0m \u001b[0mmod_name\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mload_module_mapping\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmod_name\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmod_name\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 875\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind_class\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmod_name\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 876\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 877\u001b[0m \u001b[1;31m# Load the data (which may in turn use `persistent_load` to load tensors)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",57 "\u001b[1;31mAttributeError\u001b[0m: Can't get attribute 'NewGELUActivation' on <module 'transformers.activations' from 'c:\\\\Users\\\\ADMIN\\\\textifyai\\\\lib\\\\site-packages\\\\transformers\\\\activations.py'>"58 ]59 }60 ],61 "source": [62 "model=torch.load(\"Gpt_neo_Epoch_10_Loss_031_data_5000.pth\",map_location=torch.device('cpu'))\n"63 ]64 },65 {66 "cell_type": "code",67 "execution_count": null,68 "metadata": {},69 "outputs": [],70 "source": [71 "def predict_query(input_sentence,max_len=40,temp=0.7):\n",72 " pred=[]\n",73 " seq=tokenizer(input_sentence,return_tensors='pt')['input_ids'].to(device)\n",74 " outputs=model.generate(seq,\n",75 " max_length=max_len,\n",76 " do_sample=True,\n",77 " top_p=0.95,\n",78 " #num_beams=5,\n",79 " temperature=temp,\n",80 " no_repeat_ngram_size=3,\n",81 " num_return_sequences=5\n",82 " ).to(device)\n",83 " for i,out in enumerate(outputs):\n",84 " out=tokenizer.decode(out, skip_special_tokens=True)\n",85 " idx=out.find(\"<|sep|>\")+7\n",86 " out=out[idx:]\n",87 " print(f\"Sugestion{i} :{out}\")\n",88 " pred.append(tokenizer.decode(out, skip_special_tokens=True))\n",89 " return pred\n"90 ]91 },92 {93 "cell_type": "code",94 "execution_count": 2,95 "metadata": {},96 "outputs": [97 {98 "name": "stdout",99 "output_type": "stream",100 "text": [101 "4.11.3\n"102 ]103 }104 ],105 "source": [106 "import transformers\n",107 "\n",108 "print(transformers.__version__)"109 ]110 },111 {112 "cell_type": "code",113 "execution_count": 4,114 "metadata": {},115 "outputs": [116 {117 "name": "stdout",118 "output_type": "stream",119 "text": [120 "1.8.2+cu111\n"121 ]122 }123 ],124 "source": [125 "import torch\n",126 "\n",127 "print(torch.__version__)"128 ]129 },130 {131 "cell_type": "code",132 "execution_count": 5,133 "metadata": {},134 "outputs": [135 {136 "ename": "ModuleNotFoundError",137 "evalue": "No module named 'tensorflow'",138 "output_type": "error",139 "traceback": [140 "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",141 "\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",142 "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_3544/763479854.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mtensorflow\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mtf\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"tf.__version__\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__version__\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",143 "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'tensorflow'"144 ]145 }146 ],147 "source": [148 "import tensorflow as tf\n",149 "\n",150 "print(\"tf.__version__\", tf.__version__)"151 ]152 }153 ],154 "metadata": {155 "interpreter": {156 "hash": "c2aedac36a10eb432fae2be3be58ef9112ca6433e61b95db4d37b1628d19a18a"157 },158 "kernelspec": {159 "display_name": "Python 3.7.7 64-bit ('textifyai': venv)",160 "language": "python",161 "name": "python3"162 },163 "language_info": {164 "codemirror_mode": {165 "name": "ipython",166 "version": 3167 },168 "file_extension": ".py",169 "mimetype": "text/x-python",170 "name": "python",171 "nbconvert_exporter": "python",172 "pygments_lexer": "ipython3",173 "version": "3.7.7"174 },175 "orig_nbformat": 4176 },177 "nbformat": 4,178 "nbformat_minor": 2179}180