Spaces:
Runtime error
Runtime error
File size: 26,069 Bytes
ae84b44 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 |
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "Fine tune RuDialoGPT3 on telegram chat",
"provenance": [],
"collapsed_sections": [
"uPZXtklAd0Cd",
"ESogNuUOEmj_",
"psXZnJk0Eo3J"
],
"toc_visible": true,
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/Kirili4ik/ruDialoGpt3-finetune-colab/blob/main/Fine_tune_RuDialoGPT3_on_telegram_chat.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ocoQoLlek3cb"
},
"source": [
"# Fine-Tuning DialoGPT3 on your telegram chat"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "_ptkarFllCDr"
},
"source": [
"Here is a ready-to-run code for fine-tuning a RuDialoGPT3 model using HuggingFace and PyTorch on **your telegram chat**.\n",
"\n",
"I used RuDialoGPT-3 trained on forums to fine tune. It was trained by [@Grossmend](https://github.com/Grossmend) on Russian forums. The training process took 12 days using 4x RTX 2080 Ti (2 epochs on 32GB text corpus). The training procedure of GPT-3 for dialogue is described in Grossmend's [blogpost](https://habr.com/ru/company/icl_services/blog/548244/) (in Russian).\n",
"\n",
"I have created a simple pipeline and fine tuned that model on my own exported telegram chat (~30mb json). It is in fact very easy to get the data from telegram and fine tune a model. Therefore, I made this notebook!"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "GAB9ev-Gd8lH"
},
"source": [
"If you want just to try / to talk to my fine-tuned model than go **straight to the Inference section**."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "uPZXtklAd0Cd"
},
"source": [
"## Uploading your data for fine-tuning"
]
},
{
"cell_type": "code",
"metadata": {
"id": "VL5BXKmva2-Q"
},
"source": [
"# installing huggingface datasets and accelerate \n",
"! pip install datasets transformers[sentencepiece]\n",
"! pip install accelerate\n",
"\n",
"# [optional] Login to google drive to save models\n",
"from google.colab import drive\n",
"drive.mount('/content/drive')\n",
"\n",
"# [optional] Login to wandb to track model's behaviour\n",
"'''! pip install wandb\n",
"! wandb login\n",
"wandb.init(project=\"fine tune RuDialoGPT2 on KirArChat\")'''"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"cellView": "form",
"id": "Iq78W4qhrYmN"
},
"source": [
"#@title Imports\n",
"import sys\n",
"import re\n",
"import json\n",
"\n",
"from sklearn.model_selection import train_test_split\n",
"from tqdm import tqdm\n",
"\n",
"import torch\n",
"from transformers import TextDataset, DataCollatorForLanguageModeling\n",
"from torch.utils.data import DataLoader\n",
"\n",
"from accelerate import Accelerator\n",
"from transformers import AdamW, AutoModelForSequenceClassification, get_scheduler"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "7fRNBMkYnAUV"
},
"source": [
"Next cell downloads model and tokenizer using HuggingFace.\n",
"\n",
"You can start with my version or @Grossmend's: \"Grossmend/rudialogpt3_medium_based_on_gpt2\". Moreover, you can even start with any different DialoGPT trained on your language (with the notation of |x|y|text)."
]
},
{
"cell_type": "code",
"metadata": {
"id": "fn9KxEnfaxwo"
},
"source": [
"from transformers import AutoModelForCausalLM, AutoTokenizer\n",
"\n",
"checkpoint = \"Kirili4ik/ruDialoGpt3-medium-finetuned-telegram\" \n",
"tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n",
"model = AutoModelForCausalLM.from_pretrained(checkpoint)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "SulpoPQxpJrK",
"cellView": "form"
},
"source": [
"#@title Utility functions\n",
"def get_length_param(text: str, tokenizer) -> str:\n",
" \"\"\"Maps text to 1 of 4 buckets based on length after encoding.\n",
"\n",
" Parameters\n",
" ----------\n",
" text: str\n",
" The text to be given 1 of 4 length parameters.\n",
"\n",
" tokenizer: HuggingFace tokenizer \n",
" Tokenizer that used to compute the length of the text after encoding.\n",
" For more info ee https://huggingface.co/transformers/main_classes/tokenizer.html\n",
"\n",
" Returns\n",
" -------\n",
" len_param: str\n",
" One of four buckets: \n",
" '1' for short, '2' for medium, '3' for long texts and '-' for all others. \n",
" \"\"\"\n",
" tokens_count = len(tokenizer.encode(text))\n",
" if tokens_count <= 15:\n",
" len_param = '1'\n",
" elif tokens_count <= 50:\n",
" len_param = '2'\n",
" elif tokens_count <= 256:\n",
" len_param = '3'\n",
" else:\n",
" len_param = '-'\n",
" return len_param\n",
"\n",
"\n",
"def get_user_param(text: dict, machine_name_in_chat: str) -> str:\n",
" \"\"\"Maps text by 1/0 for it to be the person or the machine in the dialog\n",
"\n",
" Parameters\n",
" ----------\n",
" text: Dict[..., 'from', ...]\n",
" Dict containing field 'from' with the name of the user who sent the message\n",
"\n",
" machine_name_in_chat: str\n",
" Str with the name of the machine - it will be predicted\n",
" \"\"\"\n",
" if text['from'] == machine_name_in_chat:\n",
" return '1' # machine\n",
" else:\n",
" return '0' # human\n",
"\n",
"\n",
"def build_text_file(data_json: dict, dest_path: str, \n",
" tokenizer, machine_name_in_chat='Кирилл Гельван'):\n",
" \"\"\"Create a text file for training in special format for ruDialoGPT-3.\n",
"\n",
" Parameters\n",
" ----------\n",
" data_json: dict\n",
" Dict containing 'text' (message) and 'from' (user who sent the message)\n",
" \n",
" dest_path: str\n",
" String containing path to write data there\n",
"\n",
" tokenizer: HuggingFace tokenizer \n",
" Tokenizer that used to compute the length of the text after encoding.\n",
" For more info ee https://huggingface.co/transformers/main_classes/tokenizer.html\n",
" \"\"\"\n",
" f = open(dest_path, 'w')\n",
" new_data = ''\n",
" for i in range(len(data_json) - 1):\n",
" message, next_message = data_json[i], data_json[i+1]\n",
" if message['text'] == '' or type(message['text']) != str:\n",
" continue\n",
" if next_message['text'] == '' or type(next_message['text']) != str:\n",
" continue\n",
"\n",
" user = get_user_param(message, machine_name_in_chat=machine_name_in_chat)\n",
" length = get_length_param(data_json[i+1]['text'], tokenizer)\n",
" message_text = re.sub(r\"\\n\", \". \", message['text'])\n",
" new_data += f\"|{user}|{length}|{message_text}{tokenizer.eos_token}\" + \"\\n\"\n",
"\n",
" f.write(new_data)\n",
"\n",
"\n",
"def load_dataset(train_path, test_path, tokenizer):\n",
" \"\"\"Creates train and test PyTorch datasets and collate_fn using HuggingFace.\n",
"\n",
" Parameters\n",
" ----------\n",
" train_path: str\n",
" String containing path to train data\n",
" \n",
" test_path: str\n",
" String containing path to test data\n",
"\n",
" tokenizer: HuggingFace tokenizer \n",
" Tokenizer that used to compute the length of the text after encoding.\n",
" For more info ee https://huggingface.co/transformers/main_classes/tokenizer.html\n",
" \"\"\"\n",
" train_dataset = TextDataset(\n",
" tokenizer = tokenizer,\n",
" file_path = train_path,\n",
" block_size = 256)\n",
" \n",
" test_dataset = TextDataset(\n",
" tokenizer = tokenizer,\n",
" file_path = test_path,\n",
" block_size = 256) \n",
" \n",
" data_collator = DataCollatorForLanguageModeling(\n",
" tokenizer=tokenizer, mlm=False\n",
" )\n",
" return train_dataset, test_dataset, data_collator"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "wS5aTe48GF_N"
},
"source": [
"1) Export your telegram chat\n",
"\n",
"\n",
"\n",
"2) Upload it to colab\n",
"\n",
"\n",
"\n",
"3) Next cell creates train and test set from it\n",
"\n",
"4) :tada:"
]
},
{
"cell_type": "code",
"metadata": {
"id": "19JKNqTS2Nu7",
"cellView": "form"
},
"source": [
"#@markdown Your telegram chat json path 'ChatExport.../YourChatName.json':\n",
"path_to_telegram_chat_json = 'example: /content/drive/MyDrive/char27.json' #@param {type : \"string\"}\n",
"#@markdown Name of the user to predict by GPT-3:\n",
"machine_name_in_chat = 'example: Kirill Gelvan' #@param {type : \"string\"}\n",
"\n",
"\n",
"with open(path_to_telegram_chat_json) as f: data = json.load(f)['messages']\n",
"\n",
"# test data is first 10% of chat, train - last 90%\n",
"train, test = data[int(len(data)*0.1):], data[:int(len(data)*0.1)]\n",
"\n",
"build_text_file(train, 'train_dataset.txt', tokenizer)\n",
"build_text_file(test, 'test_dataset.txt', tokenizer)\n",
"\n",
"print(\"Train dataset length: \" + str(len(train)) + \"samples\")\n",
"print(\"Test dataset length: \" + str(len(test)) + \"samples\")"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "qO1-aAHF6TxB"
},
"source": [
"# let's look at our data\n",
"! head -n 10 train_dataset.txt"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "J6dMhVaeIO8x"
},
"source": [
"Here the first number is the spearker number - '1' for GPT and '0' for the person. \n",
"\n",
"The second number is the lengths of the expected answer: '1' for short, '2' for medium, '3' for long texts and '-' for all others. \n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "-ty6A-qTzhya"
},
"source": [
"# Create PyTorch Datasets\n",
"train_dataset, test_dataset, data_collator = load_dataset('train_dataset.txt', 'test_dataset.txt', tokenizer)\n",
"\n",
"# Create PyTorch Dataloaders\n",
"train_loader = DataLoader(train_dataset, shuffle=True, batch_size=2, collate_fn=data_collator)\n",
"test_loader = DataLoader(test_dataset, batch_size=2, collate_fn=data_collator)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "NWhfc7ElAbkY"
},
"source": [
"# this cell checks 1 forward pass\n",
"try:\n",
" for batch in train_loader:\n",
" break\n",
" {k: v.shape for k, v in batch.items()}\n",
"\n",
" outputs = model(**batch)\n",
"except:\n",
" print(\"Unexpected error:\", sys.exc_info()[0])\n",
" raise"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "ESogNuUOEmj_"
},
"source": [
"## Fine-tuning"
]
},
{
"cell_type": "code",
"metadata": {
"id": "mZBWIviea2-Y",
"cellView": "form"
},
"source": [
"#@title Fine-tuning params\n",
"num_epochs = 3 #@param {type:\"integer\"}\n",
"optimizer = AdamW(model.parameters(), lr=3e-5) #@param\n",
"save_checkpoint_path = 'exmaple: drive/MyDrive/GPT2_checkpoint-more-data-2ep.pt' #@param {type:\"string\"}\n",
"\n",
"\n",
"num_training_steps = num_epochs * len(train_dataset)\n",
"lr_scheduler = get_scheduler(\n",
" \"linear\",\n",
" optimizer=optimizer,\n",
" num_warmup_steps=100,\n",
" num_training_steps=num_training_steps\n",
")\n",
"\n",
"accelerator = Accelerator()\n",
"train_dl, test_dl, model, optimizer = accelerator.prepare(\n",
" train_loader, test_loader, model, optimizer\n",
")\n",
"# wandb.watch(model, log=\"all\")"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "rEV3EcZOCOhw"
},
"source": [
"progress_bar = tqdm(range(num_training_steps))\n",
"\n",
"for epoch in range(num_epochs):\n",
" \n",
" ### TRAIN EPOCH\n",
" model.train()\n",
" for batch in train_dl:\n",
" optimizer.zero_grad()\n",
" outputs = model(**batch)\n",
" loss = outputs.loss\n",
" accelerator.backward(loss)\n",
" \n",
" # wandb.log({'train_loss':loss.item()})\n",
" optimizer.step()\n",
" lr_scheduler.step()\n",
" progress_bar.update(1)\n",
"\n",
" ### SAVE\n",
" torch.save({\n",
" 'model_state_dict': model.state_dict(),\n",
" }, save_checkpoint_path)\n",
" \n",
" ### VALIDATE ONCE\n",
" cum_loss = 0\n",
" model.eval()\n",
" with torch.inference_mode():\n",
" for batch in test_dl:\n",
" outputs = model(**batch)\n",
" cum_loss += float(outputs.loss.item())\n",
" \n",
" print(cum_loss/len(test_loader))\n",
" # wandb.log({'val_mean_loss':cum_loss/len(test_loader)})"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "psXZnJk0Eo3J"
},
"source": [
"## Inference"
]
},
{
"cell_type": "code",
"metadata": {
"cellView": "form",
"id": "3N13Nwd1axA4"
},
"source": [
"#@title Installs and Utility functions\n",
"\n",
"%%capture\n",
"# installing huggingface datasets and accelerate \n",
"! pip install datasets transformers[sentencepiece]\n",
"! pip install accelerate\n",
"\n",
"def get_length_param(text: str, tokenizer) -> str:\n",
" \"\"\"Maps text to 1 of 4 buckets based on length after encoding.\n",
"\n",
" Parameters\n",
" ----------\n",
" text: str\n",
" The text to be given 1 of 4 length parameters.\n",
"\n",
" tokenizer: HuggingFace tokenizer \n",
" Tokenizer that used to compute the length of the text after encoding.\n",
" For more info ee https://huggingface.co/transformers/main_classes/tokenizer.html\n",
"\n",
" Returns\n",
" -------\n",
" len_param: str\n",
" One of four buckets: \n",
" '1' for short, '2' for medium, '3' for long texts and '-' for all others. \n",
" \"\"\"\n",
" tokens_count = len(tokenizer.encode(text))\n",
" if tokens_count <= 15:\n",
" len_param = '1'\n",
" elif tokens_count <= 50:\n",
" len_param = '2'\n",
" elif tokens_count <= 256:\n",
" len_param = '3'\n",
" else:\n",
" len_param = '-'\n",
" return len_param\n",
"\n",
"\n",
"def get_user_param(text: dict, machine_name_in_chat: str) -> str:\n",
" \"\"\"Maps text by 1/0 for it to be the person or the machine in the dialogue\n",
"\n",
" Parameters\n",
" ----------\n",
" text: Dict[..., 'from', ...]\n",
" Dict containing field 'from' with the name of the user who sent the message\n",
"\n",
" machine_name_in_chat: str\n",
" Str with the name of the machine - it will be predicted\n",
" \"\"\"\n",
" if text['from'] == machine_name_in_chat:\n",
" return '1' # machine\n",
" else:\n",
" return '0' # human\n",
"\n",
"\n",
"def build_text_file(data_json: dict, dest_path: str, \n",
" tokenizer, machine_name_in_chat='Кирилл Гельван'):\n",
" \"\"\"Create a text file for training in special format for ruDialoGPT-3.\n",
"\n",
" Parameters\n",
" ----------\n",
" data_json: dict\n",
" Dict containing 'text' (message) and 'from' (user who sent the message)\n",
" \n",
" dest_path: str\n",
" String containing path to write data there\n",
"\n",
" tokenizer: HuggingFace tokenizer \n",
" Tokenizer that used to compute the length of the text after encoding.\n",
" For more info ee https://huggingface.co/transformers/main_classes/tokenizer.html\n",
" \"\"\"\n",
" f = open(dest_path, 'w')\n",
" new_data = ''\n",
" for i in range(len(data_json) - 1):\n",
" message, next_message = data_json[i], data_json[i+1]\n",
" if message['text'] == '' or type(message['text']) != str:\n",
" continue\n",
" if next_message['text'] == '' or type(next_message['text']) != str:\n",
" continue\n",
"\n",
" user = get_user_param(message, machine_name_in_chat=machine_name_in_chat)\n",
" length = get_length_param(data_json[i+1]['text'], tokenizer)\n",
" message_text = re.sub(r\"\\n\", \". \", message['text'])\n",
" new_data += f\"|{user}|{length}|{message_text}{tokenizer.eos_token}\" + \"\\n\"\n",
"\n",
" f.write(new_data)\n",
"\n",
"\n",
"def load_dataset(train_path, test_path, tokenizer):\n",
" \"\"\"Creates train and test PyTorch datasets and collate_fn using HuggingFace.\n",
"\n",
" Parameters\n",
" ----------\n",
" train_path: str\n",
" String containing path to train data\n",
" \n",
" test_path: str\n",
" String containing path to test data\n",
"\n",
" tokenizer: HuggingFace tokenizer \n",
" Tokenizer that used to compute the length of the text after encoding.\n",
" For more info ee https://huggingface.co/transformers/main_classes/tokenizer.html\n",
" \"\"\"\n",
" train_dataset = TextDataset(\n",
" tokenizer = tokenizer,\n",
" file_path = train_path,\n",
" block_size = 256)\n",
" \n",
" test_dataset = TextDataset(\n",
" tokenizer = tokenizer,\n",
" file_path = test_path,\n",
" block_size = 256) \n",
" \n",
" data_collator = DataCollatorForLanguageModeling(\n",
" tokenizer=tokenizer, mlm=False\n",
" )\n",
" return train_dataset, test_dataset, data_collator"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "vvsSRglEA0kt"
},
"source": [
"import torch\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer\n",
"\n",
"# Download checkpoint:\n",
"checkpoint = \"Kirili4ik/ruDialoGpt3-medium-finetuned-telegram\" \n",
"tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n",
"model = AutoModelForCausalLM.from_pretrained(checkpoint)\n",
"\n",
"# [optional] Insert your checkpoint if needed:\n",
"'''from google.colab import drive\n",
"drive.mount('/content/drive')\n",
"checkpoint = torch.load('drive/MyDrive/GPT2_checkpoint.pt', map_location='cpu')\n",
"model.load_state_dict(checkpoint['model_state_dict'])'''\n",
"\n",
"model = model.to('cpu')\n",
"model.eval()\n",
"print()"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "MGdCxVnOhK_K"
},
"source": [
"### INFERENCE\n",
"\n",
"chat_history_ids = torch.zeros((1, 0), dtype=torch.int)\n",
"\n",
"while True:\n",
" \n",
" next_who = input(\"Who's phrase?\\t\") #input(\"H / G?\") # Human or GPT\n",
"\n",
" # In case Human\n",
" if next_who == \"H\":\n",
" input_user = input(\"===> Human: \")\n",
" \n",
" # encode the new user input, add parameters and return a tensor in Pytorch\n",
" new_user_input_ids = tokenizer.encode(f\"|0|{get_length_param(input_user, tokenizer)}|\" \\\n",
" + input_user + tokenizer.eos_token, return_tensors=\"pt\")\n",
" # append the new user input tokens to the chat history\n",
" chat_history_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1)\n",
"\n",
" if next_who == \"G\":\n",
"\n",
" next_len = input(\"Phrase len? 1/2/3/-\\t\") #input(\"Exp. len?(-/1/2/3): \")\n",
" # encode the new user input, add parameters and return a tensor in Pytorch\n",
" new_user_input_ids = tokenizer.encode(f\"|1|{next_len}|\", return_tensors=\"pt\")\n",
" # append the new user input tokens to the chat history\n",
" chat_history_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1)\n",
" \n",
" # print(tokenizer.decode(chat_history_ids[-1])) # uncomment to see full gpt input\n",
" \n",
" # save previous len\n",
" input_len = chat_history_ids.shape[-1]\n",
" # generated a response; PS you can read about the parameters at hf.co/blog/how-to-generate\n",
" chat_history_ids = model.generate(\n",
" chat_history_ids,\n",
" num_return_sequences=1, # use for more variants, but have to print [i]\n",
" max_length=512,\n",
" no_repeat_ngram_size=3,\n",
" do_sample=True,\n",
" top_k=50,\n",
" top_p=0.9,\n",
" temperature = 0.6, # 0 for greedy\n",
" mask_token_id=tokenizer.mask_token_id,\n",
" eos_token_id=tokenizer.eos_token_id,\n",
" unk_token_id=tokenizer.unk_token_id,\n",
" pad_token_id=tokenizer.pad_token_id,\n",
" device='cpu'\n",
" )\n",
" \n",
" # pretty print last ouput tokens from bot\n",
" print(f\"===> GPT-3: {tokenizer.decode(chat_history_ids[:, input_len:][0], skip_special_tokens=True)}\")"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "mjEQiv5TMjZW"
},
"source": [
""
],
"execution_count": null,
"outputs": []
}
]
} |