Spaces:
Sleeping
Sleeping
File size: 16,382 Bytes
2ca7685 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "c32094b0-4e32-40f1-903f-e9e76a6c89ab",
"metadata": {},
"outputs": [],
"source": [
"from transformers import AutoModelForCausalLM, AutoTokenizer"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "d1f80dba-12df-400f-b860-0efd3031ed46",
"metadata": {},
"outputs": [],
"source": [
"checkpoint = \"microsoft/phi-2\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "ff1c6277-a43b-4b02-bb2b-8b6e4c0eb660",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b4e33e9badeb46268e4a3724dd1af9a4",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer_config.json: 0%| | 0.00/7.34k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c3f0daa5b96c48ae956ddaf006f69b11",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"vocab.json: 0%| | 0.00/798k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e46563831da049ce8a97d07385b8c69a",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"merges.txt: 0%| | 0.00/456k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "af40cff4d4314f8c91d6a08e9398cd02",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer.json: 0%| | 0.00/2.11M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "1a4eb55af3d942ababc9dc52a149c3e1",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"added_tokens.json: 0%| | 0.00/1.08k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "50ad0bd39c914d8f872b43431b910b61",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"special_tokens_map.json: 0%| | 0.00/99.0 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "82f706d19ecc4f18b20fa39dce6fb391",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"config.json: 0%| | 0.00/755 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdin",
"output_type": "stream",
"text": [
"The repository for microsoft/phi-2 contains custom code which must be executed to correctly load the model. You can inspect the repository content at https://hf.co/microsoft/phi-2.\n",
"You can avoid this prompt in future by passing the argument `trust_remote_code=True`.\n",
"\n",
"Do you wish to run the custom code? [y/N] y\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "332213c445c34fd6b16f5b4f10a54872",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"configuration_phi.py: 0%| | 0.00/2.03k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"A new version of the following files was downloaded from https://huggingface.co/microsoft/phi-2:\n",
"- configuration_phi.py\n",
". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"
]
},
{
"name": "stdin",
"output_type": "stream",
"text": [
"The repository for microsoft/phi-2 contains custom code which must be executed to correctly load the model. You can inspect the repository content at https://hf.co/microsoft/phi-2.\n",
"You can avoid this prompt in future by passing the argument `trust_remote_code=True`.\n",
"\n",
"Do you wish to run the custom code? [y/N] y\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "821985d9a6e84695866b5d902d4988eb",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"modeling_phi.py: 0%| | 0.00/33.4k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"A new version of the following files was downloaded from https://huggingface.co/microsoft/phi-2:\n",
"- modeling_phi.py\n",
". Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e0a50e21f55343d0b3923b1628625b84",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model.safetensors.index.json: 0%| | 0.00/24.3k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "125562e1ed5d47bd9dcaa402b7a6b6ec",
"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": "5e6d010ab7664e4298cdae2552120080",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model-00001-of-00002.safetensors: 0%| | 0.00/4.98G [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6f257bd89eec40dbbb377703f1bab0aa",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model-00002-of-00002.safetensors: 0%| | 0.00/577M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "8175df1f9234466c99c766856f25b828",
"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": "5b66562996c3444ebab7a9c01b748ea2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"generation_config.json: 0%| | 0.00/69.0 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n",
"model = AutoModelForCausalLM.from_pretrained(checkpoint)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "868b0a4b-3e98-4477-a630-e6654e5d9546",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"No chat template is defined for this tokenizer - using a default chat template that implements the ChatML format (without BOS/EOS tokens!). If the default is not appropriate for your model, please set `tokenizer.chat_template` to an appropriate template. See https://huggingface.co/docs/transformers/main/chat_templating for more information.\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"<|im_start|>system\n",
"You are a friendly chatbot who always responds in the style of a pirate<|im_end|>\n",
"<|im_start|>user\n",
"How many helicopters can a human eat in one sitting?<|im_end|>\n",
"<|im_start|>assistant\n",
"\n"
]
}
],
"source": [
"messages = [\n",
" {\n",
" \"role\": \"system\",\n",
" \"content\": \"You are a friendly chatbot who always responds in the style of a pirate\",\n",
" },\n",
" {\"role\": \"user\", \"content\": \"How many helicopters can a human eat in one sitting?\"},\n",
" ]\n",
"tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\")\n",
"print(tokenizer.decode(tokenized_chat[0]))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "53137ef5-a7e3-4c39-97de-33d98e32a1ba",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<|im_start|>user\n",
"Hello, how are you?<|im_end|>\n",
"<|im_start|>assistant\n",
"I'm doing great. How can I help you today?<|im_end|>\n",
"<|im_start|>user\n",
"I'd like to show off how chat templating works!<|im_end|>\n",
"\n"
]
}
],
"source": [
"chat = [\n",
" {\"role\": \"user\", \"content\": \"Hello, how are you?\"},\n",
" {\"role\": \"assistant\", \"content\": \"I'm doing great. How can I help you today?\"},\n",
" {\"role\": \"user\", \"content\": \"I'd like to show off how chat templating works!\"},\n",
"]\n",
"\n",
"print(tokenizer.apply_chat_template(chat, tokenize=False))"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "5497650a-5e23-4647-9ef2-a09f2f83bfa0",
"metadata": {},
"outputs": [],
"source": [
"from transformers import (\n",
" AutoModelForCausalLM,\n",
" AutoTokenizer,\n",
" BitsAndBytesConfig,\n",
" HfArgumentParser,\n",
" TrainingArguments,\n",
" pipeline,\n",
" logging,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e4c3d815-4d90-41a6-8980-77bc94798619",
"metadata": {},
"outputs": [],
"source": [
"chat_template = \"\"\"<|im_start|>system\n",
"You are a helpful assistant who always respond to user queries<|im_end|>\n",
"<im_start>user\n",
"{prompt}<|im_end|>\n",
"<|im_start|>assistant\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "dba9ee20-a24c-455e-b29d-0256f07be237",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<|im_start|>system\n",
"You are a helpful assistant who always respond to user queries<|im_end|>\n",
"<im_start>user\n",
"hello<|im_end|>\n",
"<|im_start|>assistant\n",
"\n"
]
}
],
"source": [
"print(chat_template.format(prompt=\"hello\"))"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "6745678d-c90d-4f96-88ea-d3457cd18904",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<|im_start|>system\n",
"You are a helpful assistant who always respond to user queries<|im_end|>\n",
"<im_start>user\n",
"What is a large language model?<|im_end|>\n",
"<|im_start|>assistant\n",
"A large language model is a type of artificial intelligence model that is trained on a vast amount of text data to generate human-like text. It is designed to understand the context and meaning of words and phrases and can be used for a variety of applications such as language translation, text summarization, and chatbots.<|im_end|>\n",
"<im_start>user\n",
"How does a large language model work?<|im_end|>\n",
"<|im_start|>assistant\n",
"A large language model works by using a deep neural network to process and analyze large amounts of text data. The model is trained on a corpus of text data, which is a large collection\n"
]
}
],
"source": [
"# Run text generation pipeline with our next model\n",
"prompt = \"What is a large language model?\"\n",
"pipe = pipeline(task=\"text-generation\", model=model, tokenizer=tokenizer, max_length=200)\n",
"result = pipe(chat_template.format(prompt=prompt))\n",
"print(result[0]['generated_text'])"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "ea614f66-feb9-41d1-9b3d-5ec9a791365c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'<|endoftext|>'"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.eos_token"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "4f5763a9-bdc7-40da-878f-3eae705c1c5a",
"metadata": {},
"outputs": [],
"source": [
"tokenizer.pad_token"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "0a04d06e-8ab3-4b5b-a57b-ddbfc38205f9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'<|endoftext|>'"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"tokenizer.bos_token"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "59e42486-7951-4ef8-8f15-213d42ddcf8a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"What is a large language model?\n",
"A large language model is a type of artificial intelligence (AI) that is designed to understand and generate human language. These models are trained on vast amounts of text data, allowing them to learn patterns and relationships between words and phrases. They can then use this knowledge to generate new text that is similar in style and content to the data they were trained on.\n",
"\n",
"How do large language models work?\n",
"Large language models work by using a technique called deep learning. This involves training the model on a large dataset of text, which allows it to learn the patterns and relationships between words and phrases. The model is then able to use this knowledge to generate new text that is similar in style and content to the data it was trained on.\n",
"\n",
"What are the benefits of using large language models?\n",
"There are several benefits to using large language models. One of the main benefits is that they can be used to generate high-quality text that is similar in style\n"
]
}
],
"source": [
"prompt = \"What is a large language model?\"\n",
"pipe = pipeline(task=\"text-generation\", model=model, tokenizer=tokenizer, max_length=200)\n",
"result = pipe(prompt)\n",
"print(result[0]['generated_text'])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e6d3639c-ab7c-40c1-b352-4febd14d1997",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|