File size: 54,859 Bytes
e82ea71 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# GLM-OCR to CoreML Conversion\n",
"\n",
"Converts [GLM-OCR](https://huggingface.co/aoiandroid/GLM-OCR) to CoreML for iOS/macOS.\n",
"\n",
"**Model**: CogViT visual encoder + cross-modal connector + GLM-0.5B decoder. \n",
"**Outputs**:\n",
"- `vision_encoder.mlpackage` - CogViT encoder (always exported)\n",
"- `decoder.mlpackage` - GLM-0.5B single-step decoder (if model supports it)\n",
"- `model_spec.json` - I/O shapes for Swift integration\n",
"\n",
"**Requirements**: Python 3.10+, PyTorch, transformers (main branch), coremltools 7.2+.\n",
"\n",
"**Run cells top-to-bottom.** Section 5 (quantization) and Section 6 (accuracy check) depend on Section 2."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Dependencies installed. Restart the kernel if you see import errors, then run the next cell.\n"
]
}
],
"source": [
"# Run this cell first to install dependencies into the current kernel.\n",
"import subprocess\n",
"import sys\n",
"\n",
"if sys.version_info < (3, 10):\n",
" print(\"WARNING: Python 3.10+ is required for transformers main (GLM-OCR). Current:\", sys.version)\n",
" print(\"Create a venv with Python 3.10+ and select it as the kernel to avoid 'Unrecognized processing class'.\")\n",
"\n",
"def pip_install(*packages, quiet=True):\n",
" cmd = [sys.executable, \"-m\", \"pip\", \"install\"] + ([\"-q\"] if quiet else []) + list(packages)\n",
" return subprocess.call(cmd) == 0\n",
"\n",
"pip_install(\"numpy\", \"pillow\")\n",
"pip_install(\"torch==2.3.0\", \"torchvision==0.18.0\")\n",
"\n",
"# GLM-OCR needs transformers from main. If git install fails, try PyPI (newer PyPI may include GLM-OCR).\n",
"if not pip_install(\"git+https://github.com/huggingface/transformers.git@main\"):\n",
" print(\"Git install failed (check network or build deps). Trying PyPI transformers...\")\n",
" pip_install(\"transformers>=4.45.0\")\n",
"\n",
"pip_install(\"coremltools==7.2\")\n",
"pip_install(\"huggingface_hub>=0.23.0\")\n",
"print(\"Dependencies installed. Restart the kernel if you see import errors, then run the next cell.\")\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Torch version 2.3.0 has not been tested with coremltools. You may run into unexpected errors. Torch 2.2.0 is the most recent version that has been tested.\n",
"/Users/am/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n",
"Disabling PyTorch because PyTorch >= 2.4 is required but found 2.3.0\n",
"PyTorch was not found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n"
]
}
],
"source": [
"import json\n",
"import os\n",
"from pathlib import Path\n",
"\n",
"import numpy as np\n",
"import torch\n",
"import coremltools as ct\n",
"from numpy.linalg import norm\n",
"from PIL import Image\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Load model and processor\n",
"\n",
"Using `aoiandroid/GLM-OCR` (mirror of `zai-org/GLM-OCR`). \n",
"Install transformers from main branch for GLM-OCR support: \n",
"`pip install git+https://github.com/huggingface/transformers.git`"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"PyTorch was not found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.\n"
]
},
{
"ename": "ImportError",
"evalue": "\nmodeling_auto requires the PyTorch library but it was not found in your environment. Check out the instructions on the\ninstallation page: https://pytorch.org/get-started/locally/ and follow the ones that match your environment.\nPlease note that you may need to restart your runtime after installation.\n",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[3], line 7\u001b[0m\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m----> 7\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mtransformers\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m GlmOcrProcessor, GlmOcrForConditionalGeneration\n\u001b[1;32m 8\u001b[0m processor \u001b[38;5;241m=\u001b[39m GlmOcrProcessor\u001b[38;5;241m.\u001b[39mfrom_pretrained(MODEL_ID)\n",
"\u001b[0;31mImportError\u001b[0m: cannot import name 'GlmOcrProcessor' from 'transformers' (/Users/am/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/__init__.py)",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[0;32mIn[3], line 11\u001b[0m\n\u001b[1;32m 9\u001b[0m model \u001b[38;5;241m=\u001b[39m GlmOcrForConditionalGeneration\u001b[38;5;241m.\u001b[39mfrom_pretrained(MODEL_ID, torch_dtype\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\u001b[39mfloat32)\n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m:\n\u001b[0;32m---> 11\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mtransformers\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m AutoProcessor, AutoModelForImageTextToText\n\u001b[1;32m 12\u001b[0m processor \u001b[38;5;241m=\u001b[39m AutoProcessor\u001b[38;5;241m.\u001b[39mfrom_pretrained(MODEL_ID, trust_remote_code\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 13\u001b[0m model \u001b[38;5;241m=\u001b[39m AutoModelForImageTextToText\u001b[38;5;241m.\u001b[39mfrom_pretrained(MODEL_ID, torch_dtype\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\u001b[39mfloat32, trust_remote_code\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/import_utils.py:2127\u001b[0m, in \u001b[0;36m_LazyModule.__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m 2125\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m name \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_class_to_module:\n\u001b[1;32m 2126\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 2127\u001b[0m module \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_module\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_class_to_module\u001b[49m\u001b[43m[\u001b[49m\u001b[43mname\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2128\u001b[0m value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(module, name)\n\u001b[1;32m 2129\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mModuleNotFoundError\u001b[39;00m, \u001b[38;5;167;01mRuntimeError\u001b[39;00m, \u001b[38;5;167;01mAttributeError\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 2130\u001b[0m \u001b[38;5;66;03m# V5: If trying to import a *TokenizerFast symbol, transparently fall back to the\u001b[39;00m\n\u001b[1;32m 2131\u001b[0m \u001b[38;5;66;03m# non-Fast symbol from the same module when available. This lets us keep only one\u001b[39;00m\n\u001b[1;32m 2132\u001b[0m \u001b[38;5;66;03m# backend tokenizer class while preserving legacy public names.\u001b[39;00m\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/import_utils.py:2321\u001b[0m, in \u001b[0;36m_LazyModule._get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m 2319\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m importlib\u001b[38;5;241m.\u001b[39mimport_module(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m module_name, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m)\n\u001b[1;32m 2320\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m-> 2321\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/import_utils.py:2319\u001b[0m, in \u001b[0;36m_LazyModule._get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m 2317\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21m_get_module\u001b[39m(\u001b[38;5;28mself\u001b[39m, module_name: \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m 2318\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 2319\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mimportlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mimport_module\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mmodule_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;18;43m__name__\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2320\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 2321\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n",
"File \u001b[0;32m/opt/homebrew/Cellar/python@3.10/3.10.20/Frameworks/Python.framework/Versions/3.10/lib/python3.10/importlib/__init__.py:126\u001b[0m, in \u001b[0;36mimport_module\u001b[0;34m(name, package)\u001b[0m\n\u001b[1;32m 124\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m 125\u001b[0m level \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m--> 126\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_bootstrap\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_gcd_import\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m[\u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m:\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpackage\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/models/auto/processing_auto.py:40\u001b[0m\n\u001b[1;32m 38\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfeature_extraction_auto\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m AutoFeatureExtractor\n\u001b[1;32m 39\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimage_processing_auto\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m AutoImageProcessor\n\u001b[0;32m---> 40\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mtokenization_auto\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m AutoTokenizer\n\u001b[1;32m 41\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mvideo_processing_auto\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m AutoVideoProcessor\n\u001b[1;32m 44\u001b[0m logger \u001b[38;5;241m=\u001b[39m logging\u001b[38;5;241m.\u001b[39mget_logger(\u001b[38;5;18m__name__\u001b[39m)\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:36\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[1;32m 29\u001b[0m extract_commit_hash,\n\u001b[1;32m 30\u001b[0m is_g2p_en_available,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 33\u001b[0m logging,\n\u001b[1;32m 34\u001b[0m )\n\u001b[1;32m 35\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mhub\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m cached_file\n\u001b[0;32m---> 36\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mencoder_decoder\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m EncoderDecoderConfig\n\u001b[1;32m 37\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mauto_factory\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m _LazyAutoMapping\n\u001b[1;32m 38\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mconfiguration_auto\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[1;32m 39\u001b[0m CONFIG_MAPPING_NAMES,\n\u001b[1;32m 40\u001b[0m AutoConfig,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 43\u001b[0m replace_list_option_in_docstrings,\n\u001b[1;32m 44\u001b[0m )\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/import_utils.py:2127\u001b[0m, in \u001b[0;36m_LazyModule.__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m 2125\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m name \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_class_to_module:\n\u001b[1;32m 2126\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 2127\u001b[0m module \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_module\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_class_to_module\u001b[49m\u001b[43m[\u001b[49m\u001b[43mname\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2128\u001b[0m value \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mgetattr\u001b[39m(module, name)\n\u001b[1;32m 2129\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mModuleNotFoundError\u001b[39;00m, \u001b[38;5;167;01mRuntimeError\u001b[39;00m, \u001b[38;5;167;01mAttributeError\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 2130\u001b[0m \u001b[38;5;66;03m# V5: If trying to import a *TokenizerFast symbol, transparently fall back to the\u001b[39;00m\n\u001b[1;32m 2131\u001b[0m \u001b[38;5;66;03m# non-Fast symbol from the same module when available. This lets us keep only one\u001b[39;00m\n\u001b[1;32m 2132\u001b[0m \u001b[38;5;66;03m# backend tokenizer class while preserving legacy public names.\u001b[39;00m\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/import_utils.py:2321\u001b[0m, in \u001b[0;36m_LazyModule._get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m 2319\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m importlib\u001b[38;5;241m.\u001b[39mimport_module(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m module_name, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m)\n\u001b[1;32m 2320\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m-> 2321\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/import_utils.py:2319\u001b[0m, in \u001b[0;36m_LazyModule._get_module\u001b[0;34m(self, module_name)\u001b[0m\n\u001b[1;32m 2317\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21m_get_module\u001b[39m(\u001b[38;5;28mself\u001b[39m, module_name: \u001b[38;5;28mstr\u001b[39m):\n\u001b[1;32m 2318\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 2319\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mimportlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mimport_module\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m.\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mmodule_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;18;43m__name__\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2320\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 2321\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n",
"File \u001b[0;32m/opt/homebrew/Cellar/python@3.10/3.10.20/Frameworks/Python.framework/Versions/3.10/lib/python3.10/importlib/__init__.py:126\u001b[0m, in \u001b[0;36mimport_module\u001b[0;34m(name, package)\u001b[0m\n\u001b[1;32m 124\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m 125\u001b[0m level \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m--> 126\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_bootstrap\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_gcd_import\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m[\u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m:\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpackage\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/models/encoder_decoder/configuration_encoder_decoder.py:26\u001b[0m\n\u001b[1;32m 19\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mauto\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m AutoConfig\n\u001b[1;32m 22\u001b[0m logger \u001b[38;5;241m=\u001b[39m logging\u001b[38;5;241m.\u001b[39mget_logger(\u001b[38;5;18m__name__\u001b[39m)\n\u001b[1;32m 25\u001b[0m \u001b[38;5;129;43m@auto_docstring\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mcheckpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m---> 26\u001b[0m \u001b[38;5;28;43;01mclass\u001b[39;49;00m\u001b[38;5;250;43m \u001b[39;49m\u001b[38;5;21;43;01mEncoderDecoderConfig\u001b[39;49;00m\u001b[43m(\u001b[49m\u001b[43mPreTrainedConfig\u001b[49m\u001b[43m)\u001b[49m\u001b[43m:\u001b[49m\n\u001b[1;32m 27\u001b[0m \u001b[38;5;250;43m \u001b[39;49m\u001b[38;5;124;43mr\u001b[39;49m\u001b[38;5;124;43;03m\"\"\"\u001b[39;49;00m\n\u001b[1;32m 28\u001b[0m \u001b[38;5;124;43;03m Examples:\u001b[39;49;00m\n\u001b[1;32m 29\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 54\u001b[0m \u001b[38;5;124;43;03m >>> model = EncoderDecoderModel.from_pretrained(\"my-model\", config=encoder_decoder_config)\u001b[39;49;00m\n\u001b[1;32m 55\u001b[0m \u001b[38;5;124;43;03m ```\"\"\"\u001b[39;49;00m\n\u001b[1;32m 57\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel_type\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mencoder-decoder\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/auto_docstring.py:4387\u001b[0m, in \u001b[0;36mauto_docstring.<locals>.auto_docstring_decorator\u001b[0;34m(obj)\u001b[0m\n\u001b[1;32m 4383\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m auto_method_docstring(\n\u001b[1;32m 4384\u001b[0m obj, custom_args\u001b[38;5;241m=\u001b[39mcustom_args, custom_intro\u001b[38;5;241m=\u001b[39mcustom_intro, checkpoint\u001b[38;5;241m=\u001b[39mcheckpoint\n\u001b[1;32m 4385\u001b[0m )\n\u001b[1;32m 4386\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 4387\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mauto_class_docstring\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcustom_args\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcustom_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcustom_intro\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcustom_intro\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcheckpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcheckpoint\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/auto_docstring.py:4135\u001b[0m, in \u001b[0;36mauto_class_docstring\u001b[0;34m(cls, custom_intro, custom_args, checkpoint)\u001b[0m\n\u001b[1;32m 4133\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m model_name_lowercase \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 4134\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 4135\u001b[0m model_base_class \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\n\u001b[1;32m 4136\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mgetattr\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mauto_module\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mPLACEHOLDER_TO_AUTO_MODULE\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel_class\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4137\u001b[0m \u001b[43m \u001b[49m\u001b[43mPLACEHOLDER_TO_AUTO_MODULE\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodel_class\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4138\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m[model_name_lowercase]\n\u001b[1;32m 4139\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m:\n\u001b[1;32m 4140\u001b[0m \u001b[38;5;28;01mpass\u001b[39;00m\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/import_utils.py:1975\u001b[0m, in \u001b[0;36mDummyObject.__getattribute__\u001b[0;34m(cls, key)\u001b[0m\n\u001b[1;32m 1973\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (key\u001b[38;5;241m.\u001b[39mstartswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mand\u001b[39;00m key \u001b[38;5;241m!=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_from_config\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m key \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mis_dummy\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m key \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmro\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m key \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcall\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m 1974\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__getattribute__\u001b[39m(key)\n\u001b[0;32m-> 1975\u001b[0m \u001b[43mrequires_backends\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_backends\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[0;32m~/Desktop/TranslateBlue/Notebooks/.venv_glm_ocr/lib/python3.10/site-packages/transformers/utils/import_utils.py:1961\u001b[0m, in \u001b[0;36mrequires_backends\u001b[0;34m(obj, backends)\u001b[0m\n\u001b[1;32m 1958\u001b[0m failed\u001b[38;5;241m.\u001b[39mappend(msg\u001b[38;5;241m.\u001b[39mformat(name))\n\u001b[1;32m 1960\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m failed:\n\u001b[0;32m-> 1961\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mjoin(failed))\n",
"\u001b[0;31mImportError\u001b[0m: \nmodeling_auto requires the PyTorch library but it was not found in your environment. Check out the instructions on the\ninstallation page: https://pytorch.org/get-started/locally/ and follow the ones that match your environment.\nPlease note that you may need to restart your runtime after installation.\n"
]
}
],
"source": [
"MODEL_ID = \"aoiandroid/GLM-OCR\" # or \"zai-org/GLM-OCR\"\n",
"OUTPUT_DIR = Path(\"./glm_ocr_coreml\")\n",
"OUTPUT_DIR.mkdir(parents=True, exist_ok=True)\n",
"\n",
"# Prefer transformers main (GlmOcrProcessor). Else try loading from Hub with trust_remote_code.\n",
"try:\n",
" from transformers import GlmOcrProcessor, GlmOcrForConditionalGeneration\n",
" processor = GlmOcrProcessor.from_pretrained(MODEL_ID)\n",
" model = GlmOcrForConditionalGeneration.from_pretrained(MODEL_ID, torch_dtype=torch.float32)\n",
"except ImportError:\n",
" from transformers import AutoProcessor, AutoModelForImageTextToText\n",
" processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)\n",
" model = AutoModelForImageTextToText.from_pretrained(MODEL_ID, torch_dtype=torch.float32, trust_remote_code=True)\n",
"model.eval()\n",
"\n",
"# Resolve image_size and hidden_size from config\n",
"vision_config = getattr(model.config, \"vision_config\", None)\n",
"image_size = 336\n",
"if vision_config is not None:\n",
" image_size = getattr(vision_config, \"image_size\", 336)\n",
"if isinstance(image_size, (list, tuple)):\n",
" image_size = image_size[0]\n",
"hidden_size = (\n",
" getattr(model.config, \"hidden_size\", None)\n",
" or (\n",
" getattr(model.config.text_config, \"hidden_size\", 1024)\n",
" if getattr(model.config, \"text_config\", None)\n",
" else 1024\n",
" )\n",
")\n",
"print(f\"Image size: {image_size}, hidden_size: {hidden_size}\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.1 Model structure validation\n",
"\n",
"Verify expected attributes before tracing. Raises immediately if transformers version is incompatible."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(\"=== Model structure ===\")\n",
"print(f\"Model class: {type(model).__name__}\")\n",
"\n",
"inner = getattr(model, \"model\", None)\n",
"if inner is None:\n",
" raise RuntimeError(\n",
" \"model.model not found. Inspect the loaded model structure with: print(model)\"\n",
" )\n",
"\n",
"if not hasattr(inner, \"get_image_features\"):\n",
" raise RuntimeError(\n",
" \"get_image_features not found. Install transformers from main:\\n\"\n",
" \" pip install git+https://github.com/huggingface/transformers.git\"\n",
" )\n",
"\n",
"print(f\"vision_config: {getattr(model.config, 'vision_config', 'N/A')}\")\n",
"print(f\"hidden_size : {getattr(model.config, 'hidden_size', 'N/A')}\")\n",
"\n",
"# Locate decoder submodule (for Section 4 decoder export)\n",
"_decoder_attr = None\n",
"for _name in [\"language_model\", \"text_model\", \"decoder\"]:\n",
" _obj = getattr(model, _name, None) or getattr(inner, _name, None)\n",
" if _obj is not None and hasattr(_obj, \"forward\"):\n",
" print(f\"Decoder submodule found: '{_name}'\")\n",
" _decoder_attr = _name\n",
" break\n",
"if _decoder_attr is None:\n",
" print(\"No separate decoder submodule; will use inputs_embeds path in Section 4.\")\n",
"\n",
"print(\"Structure validation OK\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Export vision encoder to CoreML\n",
"\n",
"Trace `model.model.get_image_features(pixel_values)` to extract the CogViT encoder. \n",
"Output shape: `(1, vision_seq_len, hidden_size)`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"class VisionEncoderWrapper(torch.nn.Module):\n",
" \"\"\"pixel_values (1,3,H,W) -> last_hidden_state (1, vision_seq_len, hidden_size).\"\"\"\n",
" def __init__(self, parent_model):\n",
" super().__init__()\n",
" self.base = getattr(parent_model, \"model\", parent_model)\n",
" if not hasattr(self.base, \"get_image_features\"):\n",
" raise AttributeError(\n",
" \"get_image_features not found; ensure transformers supports GLM-OCR.\"\n",
" )\n",
"\n",
" def forward(self, pixel_values: torch.Tensor):\n",
" out = self.base.get_image_features(pixel_values=pixel_values)\n",
" return out.last_hidden_state\n",
"\n",
"wrapper = VisionEncoderWrapper(model)\n",
"wrapper.eval()\n",
"\n",
"batch, channels = 1, 3\n",
"dummy_pixel = torch.randn(batch, channels, image_size, image_size, dtype=torch.float32)\n",
"\n",
"with torch.no_grad():\n",
" traced = torch.jit.trace(wrapper, (dummy_pixel,), check_trace=False, strict=False)\n",
" enc_out = traced(dummy_pixel)\n",
"\n",
"# Update hidden_size from actual trace output (overrides config-derived value)\n",
"vision_seq_len = enc_out.shape[1]\n",
"hidden_size = enc_out.shape[2]\n",
"print(f\"Vision encoder output: {enc_out.shape} (seq_len={vision_seq_len}, hidden={hidden_size})\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"input_types = [ct.TensorType(name=\"pixel_values\",\n",
" shape=(1, channels, image_size, image_size),\n",
" dtype=np.float32)]\n",
"output_types = [ct.TensorType(name=\"vision_hidden_states\")]\n",
"\n",
"# iOS16 is recommended minimum for mlprogram.\n",
"# Lower to iOS15 only after on-device testing confirms compatibility.\n",
"vision_mlmodel = ct.convert(\n",
" traced,\n",
" inputs=input_types,\n",
" outputs=output_types,\n",
" convert_to=\"mlprogram\",\n",
" minimum_deployment_target=ct.target.iOS16,\n",
" compute_units=ct.ComputeUnit.ALL,\n",
")\n",
"\n",
"vision_path = OUTPUT_DIR / \"vision_encoder.mlpackage\"\n",
"vision_mlmodel.save(str(vision_path))\n",
"print(f\"Saved: {vision_path}\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model_spec: dict = {\n",
" \"vision_encoder\": {\n",
" \"input\": {\"name\": \"pixel_values\",\n",
" \"shape\": [1, 3, int(image_size), int(image_size)], \"dtype\": \"float32\"},\n",
" \"output\": {\"name\": \"vision_hidden_states\",\n",
" \"shape\": [1, int(vision_seq_len), int(hidden_size)], \"dtype\": \"float32\"},\n",
" },\n",
" \"image_size\": int(image_size),\n",
" \"vision_seq_len\": int(vision_seq_len),\n",
" \"hidden_size\": int(hidden_size),\n",
" \"model_id\": MODEL_ID,\n",
"}\n",
"\n",
"spec_path = OUTPUT_DIR / \"model_spec.json\"\n",
"with open(spec_path, \"w\") as f:\n",
" json.dump(model_spec, f, indent=2)\n",
"print(f\"Spec saved: {spec_path}\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Save processor and config\n",
"\n",
"Save tokenizer and image processor so the iOS app can preprocess images and decode output tokens."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"processor.save_pretrained(OUTPUT_DIR)\n",
"model.config.save_pretrained(OUTPUT_DIR)\n",
"print(f\"Saved processor and config to {OUTPUT_DIR}\")\n",
"print(\"Contents:\", sorted(p.name for p in OUTPUT_DIR.iterdir()))\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Decoder export (single-step)\n",
"\n",
"Export one forward step of the GLM-0.5B decoder: \n",
"`(input_ids, encoder_hidden_states, attention_mask) -> logits`\n",
"\n",
"The iOS app calls this model in an autoregressive loop to generate text.\n",
"\n",
"**Sequence layout**: positions `[0..vision_seq_len-1]` = image tokens (from `encoder_hidden_states`), \n",
"positions `[vision_seq_len..end]` = text tokens (embedded from `input_ids`).\n",
"\n",
"**Variable-length input**: `ct.RangeDim` allows `input_ids` and `attention_mask` to accept any length \n",
"from `vision_seq_len+1` to `DECODER_MAX_LEN`. Pad to `DECODER_MAX_LEN` in Swift and mask padding with `0`.\n",
"\n",
"If this section fails, GLM-OCR may not separate vision and text forwards cleanly. \n",
"Use the vision encoder only and implement generation in Swift or Python."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"DECODER_MAX_LEN = max(256, int(vision_seq_len) + 128)\n",
"decoder_exported = False\n",
"dec_traced = None\n",
"decoder_path = None # defined here so cell 21 never raises NameError\n",
"\n",
"class DecoderStepWrapper(torch.nn.Module):\n",
" \"\"\"One decoder step: (input_ids, encoder_hidden_states, attention_mask) -> logits.\n",
"\n",
" Sequence layout:\n",
" positions [0 .. vision_seq_len-1] : image tokens from encoder_hidden_states\n",
" positions [vision_seq_len .. end] : text tokens embedded from input_ids\n",
" \"\"\"\n",
" def __init__(self, parent_model):\n",
" super().__init__()\n",
" self.inner = parent_model.model\n",
" self.lm_head = parent_model.lm_head\n",
" self.embed = parent_model.get_input_embeddings()\n",
"\n",
" def forward(\n",
" self,\n",
" input_ids: torch.Tensor, # (1, seq_len) int64\n",
" encoder_hidden_states: torch.Tensor, # (1, vision_seq_len, hidden_size)\n",
" attention_mask: torch.Tensor, # (1, seq_len) int64\n",
" ) -> torch.Tensor:\n",
" text_start = encoder_hidden_states.shape[1] # = vision_seq_len\n",
" text_len = input_ids.shape[1] - text_start\n",
"\n",
" if text_len > 0:\n",
" # Normal case: concat vision tokens + embedded text tokens\n",
" text_emb = self.embed(input_ids[:, text_start:])\n",
" inputs_embeds = torch.cat([encoder_hidden_states, text_emb], dim=1)\n",
" else:\n",
" # Edge case: no text tokens yet (first step)\n",
" inputs_embeds = encoder_hidden_states\n",
"\n",
" out = self.inner(\n",
" attention_mask=attention_mask,\n",
" inputs_embeds=inputs_embeds,\n",
" use_cache=False,\n",
" )\n",
" return self.lm_head(out.last_hidden_state)\n",
"\n",
"try:\n",
" dec_wrapper = DecoderStepWrapper(model)\n",
" dec_wrapper.eval()\n",
"\n",
" dummy_ids = torch.randint(0, 1000, (1, DECODER_MAX_LEN), dtype=torch.long)\n",
" dummy_enc = torch.randn(1, vision_seq_len, hidden_size, dtype=torch.float32)\n",
" dummy_attn = torch.ones(1, DECODER_MAX_LEN, dtype=torch.long)\n",
"\n",
" with torch.no_grad():\n",
" dec_traced = torch.jit.trace(\n",
" dec_wrapper,\n",
" (dummy_ids, dummy_enc, dummy_attn),\n",
" check_trace=False,\n",
" strict=False,\n",
" )\n",
" _dec_out = dec_traced(dummy_ids, dummy_enc, dummy_attn)\n",
" print(f\"Decoder trace OK. Output shape: {_dec_out.shape}\")\n",
"\n",
"except Exception as e:\n",
" print(f\"Decoder trace failed: {e}\")\n",
" print(\"Continuing with vision encoder only.\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if dec_traced is not None:\n",
" # RangeDim lets the model accept any seq_len from (vision_seq_len+1) to DECODER_MAX_LEN.\n",
" # In Swift, always pad input_ids/attention_mask to the same length and mask padding with 0.\n",
" seq_range = ct.RangeDim(\n",
" lower_bound=int(vision_seq_len) + 1,\n",
" upper_bound=DECODER_MAX_LEN,\n",
" )\n",
"\n",
" dec_input_types = [\n",
" ct.TensorType(name=\"input_ids\",\n",
" shape=(1, seq_range), dtype=np.int32),\n",
" ct.TensorType(name=\"encoder_hidden_states\",\n",
" shape=(1, vision_seq_len, hidden_size), dtype=np.float32),\n",
" ct.TensorType(name=\"attention_mask\",\n",
" shape=(1, seq_range), dtype=np.int32),\n",
" ]\n",
" dec_output_types = [ct.TensorType(name=\"logits\")]\n",
"\n",
" decoder_mlmodel = ct.convert(\n",
" dec_traced,\n",
" inputs=dec_input_types,\n",
" outputs=dec_output_types,\n",
" convert_to=\"mlprogram\",\n",
" minimum_deployment_target=ct.target.iOS16,\n",
" compute_units=ct.ComputeUnit.ALL,\n",
" )\n",
"\n",
" decoder_path = OUTPUT_DIR / \"decoder.mlpackage\"\n",
" decoder_mlmodel.save(str(decoder_path))\n",
" decoder_exported = True\n",
" print(f\"Saved: {decoder_path}\")\n",
"\n",
" vocab_size = int(\n",
" getattr(model.config, \"vocab_size\", None)\n",
" or getattr(getattr(model.config, \"text_config\", None), \"vocab_size\", 59392)\n",
" or 59392\n",
" )\n",
" model_spec[\"decoder\"] = {\n",
" \"input\": {\n",
" \"input_ids\": {\"shape\": [1, \"1..DECODER_MAX_LEN\"], \"dtype\": \"int32\"},\n",
" \"encoder_hidden_states\": {\"shape\": [1, int(vision_seq_len), int(hidden_size)], \"dtype\": \"float32\"},\n",
" \"attention_mask\": {\"shape\": [1, \"1..DECODER_MAX_LEN\"], \"dtype\": \"int32\"},\n",
" },\n",
" \"output\": {\"name\": \"logits\", \"shape\": [1, \"seq_len\", vocab_size]},\n",
" \"decoder_max_len\": DECODER_MAX_LEN,\n",
" \"note\": \"Pad input_ids and attention_mask to the same length; mask padding with 0.\",\n",
" }\n",
" with open(spec_path, \"w\") as f:\n",
" json.dump(model_spec, f, indent=2)\n",
" print(\"model_spec.json updated with decoder I/O.\")\n",
"else:\n",
" print(\"Decoder not exported; model_spec.json unchanged.\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5. Quantization (FP16 / INT8) and size comparison\n",
"\n",
"Reduce `vision_encoder.mlpackage` size for App Store distribution. \n",
"Run **Section 6 (accuracy verification)** after INT8 quantization.\n",
"\n",
"Both methods use `coremltools.optimize.coreml` (correct API for `mlprogram` format). \n",
"The legacy `neural_network.quantization_utils` API does **not** work with mlprogram.\n",
"\n",
"| Method | Expected size reduction |\n",
"|--------|------------------------|\n",
"| FP16 | ~50% |\n",
"| INT8 | ~75% |"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from coremltools.optimize.coreml import (\n",
" linear_quantize_weights,\n",
" OptimizationConfig,\n",
" OpLinearQuantizerConfig,\n",
")\n",
"\n",
"def _dir_size_mb(p: Path) -> float:\n",
" return sum(f.stat().st_size for f in p.rglob(\"*\") if f.is_file()) / 1e6\n",
"\n",
"# FP16 -- minimal accuracy loss, ~50% smaller\n",
"config_fp16 = OptimizationConfig(\n",
" global_config=OpLinearQuantizerConfig(\n",
" mode=\"linear_symmetric\",\n",
" dtype=np.float16,\n",
" weight_threshold=512,\n",
" )\n",
")\n",
"vision_fp16_path = None\n",
"try:\n",
" vision_fp16 = linear_quantize_weights(vision_mlmodel, config_fp16)\n",
" vision_fp16_path = OUTPUT_DIR / \"vision_encoder_fp16.mlpackage\"\n",
" vision_fp16.save(str(vision_fp16_path))\n",
" print(f\"FP16 saved: {vision_fp16_path}\")\n",
"except Exception as e:\n",
" print(f\"FP16 quantization failed: {e}\")\n",
"\n",
"# INT8 -- more compact; verify accuracy in Section 6\n",
"# dtype=np.int8 is explicit to avoid version-dependent default behaviour.\n",
"config_int8 = OptimizationConfig(\n",
" global_config=OpLinearQuantizerConfig(\n",
" mode=\"linear_symmetric\",\n",
" dtype=np.int8, # explicit: prevents coremltools version skew defaulting to float16\n",
" weight_threshold=512,\n",
" )\n",
")\n",
"vision_int8_path = None\n",
"try:\n",
" vision_int8 = linear_quantize_weights(vision_mlmodel, config_int8)\n",
" vision_int8_path = OUTPUT_DIR / \"vision_encoder_int8.mlpackage\"\n",
" vision_int8.save(str(vision_int8_path))\n",
" print(f\"INT8 saved: {vision_int8_path}\")\n",
"except Exception as e:\n",
" print(f\"INT8 quantization failed: {e}\")\n",
"\n",
"print(\"\\n=== Size comparison ===\")\n",
"for label, path in [\n",
" (\"FP32 (original)\", vision_path),\n",
" (\"FP16\", vision_fp16_path),\n",
" (\"INT8\", vision_int8_path),\n",
"]:\n",
" if path is not None and Path(str(path)).exists():\n",
" print(f\" {label:<20}: {_dir_size_mb(Path(str(path))):.1f} MB\")\n",
" else:\n",
" print(f\" {label:<20}: (not available)\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 6. Accuracy verification (PyTorch vs CoreML)\n",
"\n",
"Compare per-token cosine similarity between PyTorch traced model and CoreML FP32 model. \n",
"Expected: mean cosine similarity > 0.999. \n",
"Place a real text image at `test_image.png` for a meaningful check; random tensor is used otherwise. \n",
"INT8 quantized model is also verified if available."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def cosine_similarity_stats(a: np.ndarray, b: np.ndarray):\n",
" \"\"\"Per-token cosine similarity between two (1, T, D) arrays. Returns (mean, min).\"\"\"\n",
" sims = []\n",
" for i in range(a.shape[1]):\n",
" u, v = a[0, i], b[0, i]\n",
" denom = norm(u) * norm(v)\n",
" sims.append(float(np.dot(u, v) / denom) if denom > 0 else 1.0)\n",
" return float(np.mean(sims)), float(np.min(sims))\n",
"\n",
"# Load test image\n",
"test_image_path = Path(\"test_image.png\")\n",
"if test_image_path.exists():\n",
" _img = Image.open(test_image_path).convert(\"RGB\")\n",
" _inputs = processor(images=_img, return_tensors=\"pt\")\n",
" pixel_values = _inputs[\"pixel_values\"].to(torch.float32)\n",
" if pixel_values.shape[2] != image_size or pixel_values.shape[3] != image_size:\n",
" pixel_values = torch.nn.functional.interpolate(\n",
" pixel_values, size=(image_size, image_size),\n",
" mode=\"bilinear\", align_corners=False,\n",
" )\n",
" print(f\"Loaded: {test_image_path}\")\n",
"else:\n",
" pixel_values = torch.randn(1, 3, image_size, image_size, dtype=torch.float32)\n",
" print(\"test_image.png not found -- using random tensor (shape verification only).\")\n",
"\n",
"# PyTorch baseline\n",
"with torch.no_grad():\n",
" pt_out = traced(pixel_values).numpy() # (1, vision_seq_len, hidden_size)\n",
"\n",
"pv_np = pixel_values.numpy()\n",
"\n",
"# CoreML FP32\n",
"coreml_out = vision_mlmodel.predict({\"pixel_values\": pv_np})[\"vision_hidden_states\"]\n",
"m32, n32 = cosine_similarity_stats(pt_out, coreml_out)\n",
"print(f\"PyTorch vs CoreML FP32 -- mean cosine: {m32:.6f}, min: {n32:.6f}\")\n",
"assert m32 > 0.999, f\"FP32 accuracy too low ({m32:.6f}); check conversion settings.\"\n",
"print(\"FP32 accuracy OK\")\n",
"\n",
"# CoreML INT8 (if available)\n",
"if vision_int8_path and Path(str(vision_int8_path)).exists():\n",
" _int8_model = ct.models.MLModel(str(vision_int8_path))\n",
" int8_out = _int8_model.predict({\"pixel_values\": pv_np})[\"vision_hidden_states\"]\n",
" m8, n8 = cosine_similarity_stats(pt_out, int8_out)\n",
" print(f\"PyTorch vs CoreML INT8 -- mean cosine: {m8:.6f}, min: {n8:.6f}\")\n",
" if m8 < 0.99:\n",
" print(f\"WARNING: INT8 accuracy low ({m8:.4f}). Consider using FP16 instead.\")\n",
" else:\n",
" print(\"INT8 accuracy OK\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 7. Verify CoreML I/O\n",
"\n",
"Inspect input/output names and shapes for Xcode integration."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"loaded_v = ct.models.MLModel(str(vision_path))\n",
"spec_v = loaded_v.get_spec()\n",
"print(\"Vision encoder inputs :\", [d.name for d in spec_v.description.input])\n",
"print(\"Vision encoder outputs:\", [d.name for d in spec_v.description.output])\n",
"\n",
"if decoder_exported:\n",
" loaded_d = ct.models.MLModel(str(decoder_path))\n",
" spec_d = loaded_d.get_spec()\n",
" print(\"Decoder inputs :\", [d.name for d in spec_d.description.input])\n",
" print(\"Decoder outputs:\", [d.name for d in spec_d.description.output])\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 8. Swift integration sketch\n",
"\n",
"Add `vision_encoder.mlpackage` (and `decoder.mlpackage` if exported) to the Xcode project. \n",
"`model_spec.json` contains the exact I/O shapes needed for both models."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"swift_sketch = \"\"\"\n",
"// Swift: GLM-OCR inference with CoreML\n",
"//\n",
"// Setup:\n",
"// 1. Add vision_encoder.mlpackage to Xcode (auto-generates VisionEncoder class).\n",
"// 2. If decoder.mlpackage was exported, add it (auto-generates DecoderStep class).\n",
"// 3. Read model_spec.json at runtime to get vision_seq_len, hidden_size, DECODER_MAX_LEN.\n",
"//\n",
"// --- Vision encoder ---\n",
"// let visionModel = try VisionEncoder(configuration: .init())\n",
"// let pixelValues = preprocessImage(uiImage, size: 336) // MLMultiArray (1,3,336,336) Float32\n",
"// let visInput = VisionEncoderInput(pixel_values: pixelValues)\n",
"// let visOutput = try visionModel.prediction(input: visInput)\n",
"// let hiddenStates = visOutput.vision_hidden_states // MLMultiArray (1, vision_seq_len, hidden_size)\n",
"//\n",
"// --- Autoregressive decoding loop (requires decoder.mlpackage) ---\n",
"// var tokenIds = [Int32](repeating: 0, count: DECODER_MAX_LEN)\n",
"// var attnMask = [Int32](repeating: 0, count: DECODER_MAX_LEN)\n",
"// for i in 0..<vision_seq_len { attnMask[i] = 1 } // unmask image positions\n",
"// var pos = vision_seq_len\n",
"// let decoderModel = try DecoderStep(configuration: .init())\n",
"//\n",
"// while pos < DECODER_MAX_LEN {\n",
"// attnMask[pos] = 1 // unmask current position BEFORE inference\n",
"// let decInput = DecoderStepInput(\n",
"// input_ids: MLMultiArray(tokenIds),\n",
"// encoder_hidden_states: hiddenStates,\n",
"// attention_mask: MLMultiArray(attnMask)\n",
"// )\n",
"// let logits = try decoderModel.prediction(input: decInput).logits\n",
"// let nextToken = argmax(logits, at: pos) // read logit at current position\n",
"// if nextToken == eosTokenId { break }\n",
"// tokenIds[pos] = Int32(nextToken)\n",
"// pos += 1\n",
"// }\n",
"// let outputText = tokenizer.decode(tokenIds.prefix(pos))\n",
"\"\"\"\n",
"print(swift_sketch)\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv_glm_ocr",
"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": "3.10.20"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
|