File size: 41,313 Bytes
d22347e |
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 |
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "T4"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "code",
"source": [
"!pip install datasets"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "c-WoJQeGyPlG",
"outputId": "9ff1fe05-13fc-4046-c45e-f7396b1f2250"
},
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting datasets\n",
" Downloading datasets-2.19.1-py3-none-any.whl (542 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m542.0/542.0 kB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.14.0)\n",
"Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.25.2)\n",
"Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (14.0.2)\n",
"Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n",
"Collecting dill<0.3.9,>=0.3.0 (from datasets)\n",
" Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m17.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.0.3)\n",
"Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.4)\n",
"Collecting xxhash (from datasets)\n",
" Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m29.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting multiprocess (from datasets)\n",
" Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m21.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: fsspec[http]<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n",
"Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.5)\n",
"Requirement already satisfied: huggingface-hub>=0.21.2 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.23.1)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.0)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n",
"Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n",
"Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n",
"Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.11.0)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2024.2.2)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n",
"Installing collected packages: xxhash, dill, multiprocess, datasets\n",
"Successfully installed datasets-2.19.1 dill-0.3.8 multiprocess-0.70.16 xxhash-3.4.1\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pip install \"unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git\"\n",
"!pip install --no-deps xformers trl peft accelerate bitsandbytes"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "bNRY4EekyVv0",
"outputId": "337e20ec-32fb-473a-ce75-1b4602b3e05a"
},
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git\n",
" Cloning https://github.com/unslothai/unsloth.git to /tmp/pip-install-yz9b4cgg/unsloth_b0255de764894292a5ad70b60132ae17\n",
" Running command git clone --filter=blob:none --quiet https://github.com/unslothai/unsloth.git /tmp/pip-install-yz9b4cgg/unsloth_b0255de764894292a5ad70b60132ae17\n",
" Resolved https://github.com/unslothai/unsloth.git to commit cd1b44878686972d1de60e905215825da330f1e1\n",
" Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting tyro (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git)\n",
" Downloading tyro-0.8.4-py3-none-any.whl (102 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m102.4/102.4 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: transformers>=4.38.2 in /usr/local/lib/python3.10/dist-packages (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (4.41.1)\n",
"Requirement already satisfied: datasets>=2.16.0 in /usr/local/lib/python3.10/dist-packages (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2.19.1)\n",
"Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.1.99)\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (4.66.4)\n",
"Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (5.9.5)\n",
"Requirement already satisfied: wheel>=0.42.0 in /usr/local/lib/python3.10/dist-packages (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.43.0)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (1.25.2)\n",
"Requirement already satisfied: protobuf<4.0.0 in /usr/local/lib/python3.10/dist-packages (from unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (3.20.3)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (3.14.0)\n",
"Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (14.0.2)\n",
"Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.6)\n",
"Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.3.8)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2.0.3)\n",
"Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2.31.0)\n",
"Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (3.4.1)\n",
"Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.70.16)\n",
"Requirement already satisfied: fsspec[http]<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2023.6.0)\n",
"Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (3.9.5)\n",
"Requirement already satisfied: huggingface-hub>=0.21.2 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.23.1)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (24.0)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (6.0.1)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.38.2->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2024.5.15)\n",
"Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.38.2->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.19.1)\n",
"Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.38.2->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.4.3)\n",
"Requirement already satisfied: docstring-parser>=0.14.1 in /usr/local/lib/python3.10/dist-packages (from tyro->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.16)\n",
"Requirement already satisfied: typing-extensions>=4.7.0 in /usr/local/lib/python3.10/dist-packages (from tyro->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (4.11.0)\n",
"Requirement already satisfied: rich>=11.1.0 in /usr/local/lib/python3.10/dist-packages (from tyro->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (13.7.1)\n",
"Collecting shtab>=1.5.6 (from tyro->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git)\n",
" Downloading shtab-1.7.1-py3-none-any.whl (14 kB)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (1.3.1)\n",
"Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (23.2.0)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (1.4.1)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (6.0.5)\n",
"Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (1.9.4)\n",
"Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (4.0.3)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2024.2.2)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=11.1.0->tyro->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (3.0.0)\n",
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=11.1.0->tyro->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2.16.1)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2023.4)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (2024.1)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=11.1.0->tyro->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (0.1.2)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets>=2.16.0->unsloth[colab-new]@ git+https://github.com/unslothai/unsloth.git) (1.16.0)\n",
"Building wheels for collected packages: unsloth\n",
" Building wheel for unsloth (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for unsloth: filename=unsloth-2024.5-py3-none-any.whl size=109128 sha256=d07640c7a49efaa3dcfbf645a27e7b8a03b25d97d757255165955b28d50c7c65\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-74zy8n65/wheels/ed/d4/e9/76fb290ee3df0a5fc21ce5c2c788e29e9607a2353d8342fd0d\n",
"Successfully built unsloth\n",
"Installing collected packages: unsloth, shtab, tyro\n",
"Successfully installed shtab-1.7.1 tyro-0.8.4 unsloth-2024.5\n",
"Collecting xformers\n",
" Downloading xformers-0.0.26.post1-cp310-cp310-manylinux2014_x86_64.whl (222.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m222.7/222.7 MB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting trl\n",
" Downloading trl-0.8.6-py3-none-any.whl (245 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m245.2/245.2 kB\u001b[0m \u001b[31m36.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting peft\n",
" Downloading peft-0.11.1-py3-none-any.whl (251 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m251.6/251.6 kB\u001b[0m \u001b[31m38.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting accelerate\n",
" Downloading accelerate-0.30.1-py3-none-any.whl (302 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.6/302.6 kB\u001b[0m \u001b[31m43.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting bitsandbytes\n",
" Downloading bitsandbytes-0.43.1-py3-none-manylinux_2_24_x86_64.whl (119.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m119.8/119.8 MB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hInstalling collected packages: bitsandbytes, xformers, trl, peft, accelerate\n",
"Successfully installed accelerate-0.30.1 bitsandbytes-0.43.1 peft-0.11.1 trl-0.8.6 xformers-0.0.26.post1\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"from datasets import load_dataset,Dataset\n",
"import torch\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig\n",
"from peft import prepare_model_for_kbit_training, LoraConfig, TaskType, get_peft_model\n",
"from transformers import TrainingArguments\n",
"from trl import SFTTrainer\n",
"from peft import AutoPeftModelForCausalLM, PeftModel\n",
"from transformers import AutoModelForCausalLM\n",
"import os\n",
"from transformers import GenerationConfig\n",
"from time import perf_counter\n",
"from unsloth import FastLanguageModel\n",
"from unsloth import is_bfloat16_supported"
],
"metadata": {
"id": "-ixC4T7wztdx"
},
"execution_count": 38,
"outputs": []
},
{
"cell_type": "code",
"source": [
"model_id = \"unsloth/tinyllama-bnb-4bit\"\n",
"data_id = 'Malikeh1375/medical-question-answering-datasets'\n",
"output_model = 'doctor_chat_LLM_150_unsloth'\n",
"\n",
"def prepare_train_data(data_id):\n",
" data = load_dataset(data_id, 'all-processed',split=\"train\")\n",
" data_df = data.to_pandas()\n",
" data_df[\"text\"] = data_df[['instruction','input','output']].apply(lambda x: \"<|Instruction|>\\n\" + x[\"instruction\"] +\"</s>\\n<|Input|>\\n\" + x[\"input\"] + \"</s>\\n<|Output|>\\n\"+x['output']+\"</s>\", axis=1)\n",
" data = Dataset.from_pandas(data_df)\n",
" return data\n",
"\n",
"train_data = prepare_train_data(data_id).shuffle(seed=42).select(range(500))\n",
"\n",
"print(train_data[0]['text'])"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ZHptL3OqEhdi",
"outputId": "ccd438ee-f4d1-46e4-dda7-2cae7847aa69"
},
"execution_count": 50,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"<|Instruction|>\n",
"If you are a doctor, please answer the medical questions based on the patient's description.</s>\n",
"<|Input|>\n",
"Hi, may I answer your health queries right now ? Please type your query here...SIR MY PROBLEM IS SOME TIME AFTER URINATION ,I FELT LIKE SOME THING IS COMING FROM MY PENIS & A CAN SEE THIS IS OILY THICKY SOME DROPE IS COMING & IT IS VERY OILY & LUBRICANT TYPE WHAT IS THIS I M VERY WORRIED</s>\n",
"<|Output|>\n",
"hi, if you are sexually active then there is a high chance that you may have had a sexually transmitted disease. you need to see a doctor and the fluid would be tested for different types of bacteria, fungi and viruses. you may also need some antibiotics to ensure that you are treated properly. if you are not sexually active it is better also to have the fluid checked for its composition so that we will be able to provide proper management and treatment for your case. hope i have answered your query. let me know if i can assist you further.</s>\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"print(train_data[1]['text'])"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "57puJnWr40rp",
"outputId": "13d46aa8-cf0d-4c67-b0b4-fbd01fb7d4be"
},
"execution_count": 51,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"<|Instruction|>\n",
"If you are a doctor, please answer the medical questions based on the patient's description.</s>\n",
"<|Input|>\n",
"Hi,i have undergone several tests like uv scan,trans vaginal scan and blood tests including hormonal tests and thyroid tests etc. but everything seems normal.we r trying for pregnancy for last one and half year and he too had normal sperm count but we couldn t succeed.i m using trufol,benforce-m and a to z gold multiitamin tablet from before 1 month.i used to get regular periods.in december i have taken premoult to delay my period for some reason and after stopping it i have my period after 3 days ie. dec 25th and in january i have period on 20th but know i missed my period till know and pregnancy test is negative.is their any problem with medicines i mentioned above for delayed period.</s>\n",
"<|Output|>\n",
"hi, thanks for your question. i don't think the medicine you are on, or have had could have caused this period problem. you have not provided the details of your test results & from the medicine you are taking i have guessed that you may have an ovulation problem (since you are on metformin, are unable to conceive & have delayed periods). so, my suggestion for you is to register yourself at a good fertility clinic with your partner & get yourself fully evaluated. once a cause is found you may be offered a specific treatment which may be ovulation induction in your case. wish you best of luck</s>\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"train_data"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "F9xwbYPD107L",
"outputId": "a17be6ac-de80-4013-f17d-f8d64794f335"
},
"execution_count": 52,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"Dataset({\n",
" features: ['instruction', 'input', 'output', '__index_level_0__', 'text'],\n",
" num_rows: 500\n",
"})"
]
},
"metadata": {},
"execution_count": 52
}
]
},
{
"cell_type": "code",
"source": [
"model, tokenizer = FastLanguageModel.from_pretrained(\n",
" model_name = \"unsloth/tinyllama-bnb-4bit\", # \"unsloth/tinyllama\" for 16bit loading\n",
" max_seq_length = 1500,\n",
" dtype = None,\n",
" load_in_4bit = True,\n",
" # token = \"hf_...\", # use one if using gated models like meta-llama/Llama-2-7b-hf\n",
")\n",
"\n",
"print(model)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 499
},
"id": "Ic5lF0DNyLji",
"outputId": "8c70c2f6-af0d-4b99-c60f-a7dc81df06d4"
},
"execution_count": 54,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"==((====))== Unsloth: Fast Llama patching release 2024.5\n",
" \\\\ /| GPU: Tesla T4. Max memory: 14.748 GB. Platform = Linux.\n",
"O^O/ \\_/ \\ Pytorch: 2.3.0+cu121. CUDA = 7.5. CUDA Toolkit = 12.1.\n",
"\\ / Bfloat16 = FALSE. Xformers = 0.0.26.post1. FA = False.\n",
" \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n"
]
},
{
"output_type": "error",
"ename": "ValueError",
"evalue": "Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit the quantized model. If you want to dispatch the model on the CPU or the disk while keeping these modules in 32-bit, you need to set `load_in_8bit_fp32_cpu_offload=True` and pass a custom `device_map` to `from_pretrained`. Check https://huggingface.co./docs/transformers/main/en/main_classes/quantization#offload-between-cpu-and-gpu for more details. ",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-54-43ef74bf5388>\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m model, tokenizer = FastLanguageModel.from_pretrained(\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0mmodel_name\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"unsloth/tinyllama-bnb-4bit\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;31m# \"unsloth/tinyllama\" for 16bit loading\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mmax_seq_length\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m1000\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mdtype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mload_in_4bit\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/unsloth/models/loader.py\u001b[0m in \u001b[0;36mfrom_pretrained\u001b[0;34m(model_name, max_seq_length, dtype, load_in_4bit, token, device_map, rope_scaling, fix_tokenizer, trust_remote_code, use_gradient_checkpointing, resize_model_vocab, *args, **kwargs)\u001b[0m\n\u001b[1;32m 140\u001b[0m \u001b[0;32mpass\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 141\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 142\u001b[0;31m model, tokenizer = dispatch_model.from_pretrained(\n\u001b[0m\u001b[1;32m 143\u001b[0m \u001b[0mmodel_name\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 144\u001b[0m \u001b[0mmax_seq_length\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmax_seq_length\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/unsloth/models/llama.py\u001b[0m in \u001b[0;36mfrom_pretrained\u001b[0;34m(model_name, max_seq_length, dtype, load_in_4bit, token, device_map, rope_scaling, fix_tokenizer, model_patcher, tokenizer_name, trust_remote_code, **kwargs)\u001b[0m\n\u001b[1;32m 1133\u001b[0m )\n\u001b[1;32m 1134\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1135\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0merror\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1136\u001b[0m \u001b[0;32mpass\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1137\u001b[0m \u001b[0;32mpass\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/unsloth/models/llama.py\u001b[0m in \u001b[0;36mfrom_pretrained\u001b[0;34m(model_name, max_seq_length, dtype, load_in_4bit, token, device_map, rope_scaling, fix_tokenizer, model_patcher, tokenizer_name, trust_remote_code, **kwargs)\u001b[0m\n\u001b[1;32m 1104\u001b[0m \u001b[0mmax_position_embeddings\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmax_seq_length\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmodel_max_seq_length\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1105\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1106\u001b[0;31m model = AutoModelForCausalLM.from_pretrained(\n\u001b[0m\u001b[1;32m 1107\u001b[0m \u001b[0mmodel_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1108\u001b[0m \u001b[0mdevice_map\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdevice_map\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py\u001b[0m in \u001b[0;36mfrom_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 561\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mcls\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_model_mapping\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkeys\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 562\u001b[0m \u001b[0mmodel_class\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_get_model_class\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcls\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_model_mapping\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 563\u001b[0;31m return model_class.from_pretrained(\n\u001b[0m\u001b[1;32m 564\u001b[0m \u001b[0mpretrained_model_name_or_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0mmodel_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconfig\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mhub_kwargs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 565\u001b[0m )\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py\u001b[0m in \u001b[0;36mfrom_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m 3701\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3702\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mhf_quantizer\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3703\u001b[0;31m \u001b[0mhf_quantizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalidate_environment\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdevice_map\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdevice_map\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3704\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3705\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mdevice_map\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/transformers/quantizers/quantizer_bnb_4bit.py\u001b[0m in \u001b[0;36mvalidate_environment\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 83\u001b[0m }\n\u001b[1;32m 84\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;34m\"cpu\"\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdevice_map_without_lm_head\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0;34m\"disk\"\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mdevice_map_without_lm_head\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 85\u001b[0;31m raise ValueError(\n\u001b[0m\u001b[1;32m 86\u001b[0m \u001b[0;34m\"Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit the \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 87\u001b[0m \u001b[0;34m\"quantized model. If you want to dispatch the model on the CPU or the disk while keeping these modules \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mValueError\u001b[0m: Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit the quantized model. If you want to dispatch the model on the CPU or the disk while keeping these modules in 32-bit, you need to set `load_in_8bit_fp32_cpu_offload=True` and pass a custom `device_map` to `from_pretrained`. Check https://huggingface.co./docs/transformers/main/en/main_classes/quantization#offload-between-cpu-and-gpu for more details. "
]
}
]
},
{
"cell_type": "code",
"source": [
"model = FastLanguageModel.get_peft_model(\n",
" model,\n",
" r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128\n",
" target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n",
" \"gate_proj\", \"up_proj\", \"down_proj\",],\n",
" lora_alpha = 32,\n",
" lora_dropout = 0, # Currently only supports dropout = 0\n",
" bias = \"none\", # Currently only supports bias = \"none\"\n",
" use_gradient_checkpointing = True, # @@@ IF YOU GET OUT OF MEMORY - set to True @@@\n",
" random_state = 42,\n",
" use_rslora = False, # We support rank stabilized LoRA\n",
" loftq_config = None, # And LoftQ\n",
")"
],
"metadata": {
"id": "-EGbwycpzb4j"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"trainer = SFTTrainer(\n",
" model = model,\n",
" tokenizer = tokenizer,\n",
" train_dataset = train_data,\n",
" dataset_text_field = \"text\",\n",
" max_seq_length = 1500,\n",
" packing = True, # Packs short sequences together to save time!\n",
" args = TrainingArguments(\n",
" per_device_train_batch_size = 8,\n",
" gradient_accumulation_steps = 4,\n",
" warmup_ratio = 0.1,\n",
" num_train_epochs = 10,\n",
" max_steps=200,\n",
" learning_rate = 2e-5,\n",
" fp16 = not is_bfloat16_supported(),\n",
" bf16 = is_bfloat16_supported(),\n",
" logging_steps = 1,\n",
" optim = \"adamw_8bit\",\n",
" weight_decay = 0.1,\n",
" lr_scheduler_type = \"linear\",\n",
" output_dir = output_model,\n",
" ),\n",
")\n",
"trainer.train()"
],
"metadata": {
"id": "Qy6yK4FLze4f"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"train_data[1]['text']"
],
"metadata": {
"id": "wBEwT9up9DSz"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"FastLanguageModel.for_inference(model)\n",
"\n",
"def formatted_prompt(Instruction,input)-> str:\n",
" return f\"<|Instruction|>\\n{Instruction}</s>\\n<|input|>\\n{input}</s>\\n<|output|>\"\n",
"\n",
"def generate_response(Instruction,user_input):\n",
"\n",
" prompt = formatted_prompt(Instruction,user_input)\n",
" print(prompt)\n",
"\n",
" start_time = perf_counter()\n",
"\n",
" inputs = tokenizer(prompt, return_tensors=\"pt\").to('cuda')\n",
"\n",
" outputs = model.generate(**inputs, max_new_tokens = 150, use_cache = True)\n",
" print(tokenizer.batch_decode(outputs))\n",
" output_time = perf_counter() - start_time\n",
" print(f\"Time taken for inference: {round(output_time,2)} seconds\")\n",
"\n",
"\n",
"Instruction = \"If you are a doctor, please answer the medical questions based on the patient's description.\"\n",
"user_input = 'I am a 20 year old boy.I am having frequent headaches what should i do?What temprory steps should i take?'\n",
"\n",
"generate_response(Instruction,user_input)"
],
"metadata": {
"id": "32lR_kynzmuv"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "9FulpdS10A_X"
},
"execution_count": null,
"outputs": []
}
]
} |