Hugging Face's logo

Spaces:
ycwhencpp
/
final-iteration
Paused

App Files Community
anuragredbus commited on
Commit
eb1d764
·
1 Parent(s): 8d09986

fix: notebook loads Qwen without bitsandbytes on Mac; optional training deps

Browse files

- Use 4-bit only when CUDA + bitsandbytes available
- Fallback fp16 MPS / fp32 CPU with clear message
- Add project optional-dependencies training extra for Colab stack

Made-with: Cursor

Files changed (2) hide show
  1. pyproject.toml +10 -0
  2. training/train_grpo.ipynb +167 -41
pyproject.toml CHANGED
@@ -26,6 +26,16 @@ dev = [
26
  "pytest>=8.0.0",
27
  "pytest-cov>=4.0.0",
28
  ]
 
 
 
 
 
 
 
 
 
 
29
 
30
  [project.scripts]
31
  # Server entry point - enables running via: uv run --project . server
 
26
  "pytest>=8.0.0",
27
  "pytest-cov>=4.0.0",
28
  ]
29
+ # Colab / CUDA: 4-bit QLoRA. On Mac without CUDA, notebook falls back to fp16 (MPS) / fp32 (CPU).
30
+ training = [
31
+ "bitsandbytes>=0.46.1",
32
+ "transformers>=4.45.0",
33
+ "accelerate>=1.0.0",
34
+ "peft>=0.10.0",
35
+ "trl>=0.8.0",
36
+ "datasets>=2.0.0",
37
+ "torch",
38
+ ]
39
 
40
  [project.scripts]
41
  # Server entry point - enables running via: uv run --project . server
training/train_grpo.ipynb CHANGED
@@ -32,7 +32,7 @@
32
  "!pip install -q pydantic httpx\n",
33
  "!pip install -q \"openenv-core[core]>=0.2.2\""
34
  ],
35
- "execution_count": 5,
36
  "outputs": [
37
  {
38
  "output_type": "stream",
@@ -133,23 +133,17 @@
133
  "print(f\"Commit: {commit}\")\n",
134
  "print(f\"Plots dir: {PLOTS_DIR}\")"
135
  ],
136
- "execution_count": 6,
137
  "outputs": [
138
  {
139
  "output_type": "stream",
140
  "text": [
141
- "fatal: could not create leading directories of '/content/viral-posts-env': Read-only file system\n"
142
- ]
143
- },
144
- {
145
- "output_type": "error",
146
- "ename": "FileNotFoundError",
147
- "evalue": "[Errno 2] No such file or directory: '/content/viral-posts-env'",
148
- "traceback": [
149
- "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
150
- "\u001b[31mFileNotFoundError\u001b[39m Traceback (most recent call last)",
151
- "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[6]\u001b[39m\u001b[32m, line 13\u001b[39m\n\u001b[32m 9\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m os.path.exists(REPO_DIR):\n\u001b[32m 10\u001b[39m get_ipython().system(\u001b[33m'rm -rf {REPO_DIR}'\u001b[39m)\n\u001b[32m 11\u001b[39m \n\u001b[32m 12\u001b[39m get_ipython().system(\u001b[33m'git clone --branch {REPO_BRANCH} --depth 1 {REPO_URL} {REPO_DIR}'\u001b[39m)\n\u001b[32m---> \u001b[39m\u001b[32m13\u001b[39m os.chdir(REPO_DIR)\n\u001b[32m 14\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m REPO_DIR \u001b[38;5;28;01mnot\u001b[39;00m \u001b[38;5;28;01min\u001b[39;00m sys.path:\n\u001b[32m 15\u001b[39m sys.path.insert(\u001b[32m0\u001b[39m, REPO_DIR)\n\u001b[32m 16\u001b[39m \n",
152
- "\u001b[31mFileNotFoundError\u001b[39m: [Errno 2] No such file or directory: '/content/viral-posts-env'"
153
  ]
154
  }
155
  ]
@@ -206,8 +200,23 @@
206
  " \"Restart runtime and run from Cell 1 again (clean clone on hack1).\"\n",
207
  ")"
208
  ],
209
- "execution_count": null,
210
- "outputs": []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
211
  },
212
  {
213
  "cell_type": "markdown",
@@ -298,8 +307,15 @@
298
  "\n",
299
  "print(\"Agents and episode runner defined.\")"
300
  ],
301
- "execution_count": null,
302
- "outputs": []
 
 
 
 
 
 
 
303
  },
304
  {
305
  "cell_type": "code",
@@ -339,8 +355,45 @@
339
  " scores = [baseline_results[name][t][\"grader_score\"] for t in TASKS]\n",
340
  " print(f\"{name:<14s} {scores[0]:>10.4f} {scores[1]:>12.4f} {scores[2]:>14.4f} {sum(scores)/3:>8.4f}\")"
341
  ],
342
- "execution_count": null,
343
- "outputs": []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
344
  },
345
  {
346
  "cell_type": "code",
@@ -363,8 +416,18 @@
363
  "fig.savefig(f\"{PLOTS_DIR}/baseline_leaderboard.png\", dpi=150, bbox_inches='tight')\n",
364
  "plt.show()"
365
  ],
366
- "execution_count": null,
367
- "outputs": []
 
 
 
 
 
 
 
 
 
 
368
  },
369
  {
370
  "cell_type": "markdown",
@@ -379,31 +442,94 @@
379
  "cell_type": "code",
380
  "metadata": {},
381
  "source": [
382
- "# Cell 7: Load model\n",
383
- "from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig\n",
384
  "\n",
385
  "MODEL_NAME = \"Qwen/Qwen2.5-1.5B-Instruct\"\n",
386
  "\n",
387
- "bnb_config = BitsAndBytesConfig(\n",
388
- " load_in_4bit=True,\n",
389
- " bnb_4bit_quant_type=\"nf4\",\n",
390
- " bnb_4bit_compute_dtype=torch.float16,\n",
391
- " bnb_4bit_use_double_quant=True,\n",
392
- ")\n",
393
- "\n",
394
- "print(f\"Loading {MODEL_NAME} (4-bit quantized)...\")\n",
395
  "tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)\n",
396
- "model = AutoModelForCausalLM.from_pretrained(\n",
397
- " MODEL_NAME, trust_remote_code=True,\n",
398
- " quantization_config=bnb_config,\n",
399
- " device_map=\"auto\",\n",
400
- ")\n",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
401
  "model.eval()\n",
402
- "print(f\"Model loaded. Device: {model.device}\")\n",
403
- "print(f\"Memory: {torch.cuda.memory_allocated()/1e9:.1f} GB\")"
 
 
 
 
 
404
  ],
405
- "execution_count": null,
406
- "outputs": []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
407
  },
408
  {
409
  "cell_type": "code",
 
32
  "!pip install -q pydantic httpx\n",
33
  "!pip install -q \"openenv-core[core]>=0.2.2\""
34
  ],
35
+ "execution_count": 1,
36
  "outputs": [
37
  {
38
  "output_type": "stream",
 
133
  "print(f\"Commit: {commit}\")\n",
134
  "print(f\"Plots dir: {PLOTS_DIR}\")"
135
  ],
136
+ "execution_count": 2,
137
  "outputs": [
138
  {
139
  "output_type": "stream",
140
  "text": [
141
+ "Mode: local\n",
142
+ "Repo root: /Users/anurag.c/viral-posts-env\n",
143
+ "Working dir: /Users/anurag.c/viral-posts-env\n",
144
+ "Branch: hack1\n",
145
+ "Commit: b5ad200\n",
146
+ "Plots dir: /Users/anurag.c/viral-posts-env/plots\n"
 
 
 
 
 
 
147
  ]
148
  }
149
  ]
 
200
  " \"Restart runtime and run from Cell 1 again (clean clone on hack1).\"\n",
201
  ")"
202
  ],
203
+ "execution_count": 3,
204
+ "outputs": [
205
+ {
206
+ "output_type": "stream",
207
+ "text": [
208
+ "/Users/anurag.c/viral-posts-env/.venv/lib/python3.14/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",
209
+ " from .autonotebook import tqdm as notebook_tqdm\n"
210
+ ]
211
+ },
212
+ {
213
+ "output_type": "stream",
214
+ "text": [
215
+ "GPU: CPU\n",
216
+ "Tags: 114, Topics: 100, Horizon: 30 days\n"
217
+ ]
218
+ }
219
+ ]
220
  },
221
  {
222
  "cell_type": "markdown",
 
307
  "\n",
308
  "print(\"Agents and episode runner defined.\")"
309
  ],
310
+ "execution_count": 4,
311
+ "outputs": [
312
+ {
313
+ "output_type": "stream",
314
+ "text": [
315
+ "Agents and episode runner defined.\n"
316
+ ]
317
+ }
318
+ ]
319
  },
320
  {
321
  "cell_type": "code",
 
355
  " scores = [baseline_results[name][t][\"grader_score\"] for t in TASKS]\n",
356
  " print(f\"{name:<14s} {scores[0]:>10.4f} {scores[1]:>12.4f} {scores[2]:>14.4f} {sum(scores)/3:>8.4f}\")"
357
  ],
358
+ "execution_count": 5,
359
+ "outputs": [
360
+ {
361
+ "output_type": "stream",
362
+ "text": [
363
+ "Running heuristic baselines (5 agents × 3 tasks)...\n",
364
+ "======================================================================\n",
365
+ " always_rest | monthly_engage | score=0.0000 | energy=1.00\n",
366
+ " always_rest | monthly_strategic | score=0.1750 | energy=1.00\n",
367
+ " always_rest | monthly_competitive | score=0.0350 | energy=1.00\n",
368
+ "\n",
369
+ " spam | monthly_engage | score=0.0042 | energy=0.00\n",
370
+ " spam | monthly_strategic | score=0.0075 | energy=0.00\n",
371
+ " spam | monthly_competitive | score=0.0000 | energy=0.00\n",
372
+ "\n",
373
+ " random | monthly_engage | score=0.5389 | energy=0.92\n",
374
+ " random | monthly_strategic | score=0.6403 | energy=0.92\n",
375
+ " random | monthly_competitive | score=0.6678 | energy=0.92\n",
376
+ "\n",
377
+ " minimal | monthly_engage | score=0.4145 | energy=1.00\n",
378
+ " minimal | monthly_strategic | score=0.7220 | energy=1.00\n",
379
+ " minimal | monthly_competitive | score=0.3850 | energy=1.00\n",
380
+ "\n",
381
+ " smart | monthly_engage | score=0.7883 | energy=1.00\n",
382
+ " smart | monthly_strategic | score=0.8932 | energy=1.00\n",
383
+ " smart | monthly_competitive | score=0.8986 | energy=1.00\n",
384
+ "\n",
385
+ "\n",
386
+ "LEADERBOARD\n",
387
+ "Agent Engage Strategic Competitive Avg\n",
388
+ "------------------------------------------------------------\n",
389
+ "always_rest 0.0000 0.1750 0.0350 0.0700\n",
390
+ "spam 0.0042 0.0075 0.0000 0.0039\n",
391
+ "random 0.5389 0.6403 0.6678 0.6157\n",
392
+ "minimal 0.4145 0.7220 0.3850 0.5072\n",
393
+ "smart 0.7883 0.8932 0.8986 0.8600\n"
394
+ ]
395
+ }
396
+ ]
397
  },
398
  {
399
  "cell_type": "code",
 
416
  "fig.savefig(f\"{PLOTS_DIR}/baseline_leaderboard.png\", dpi=150, bbox_inches='tight')\n",
417
  "plt.show()"
418
  ],
419
+ "execution_count": 6,
420
+ "outputs": [
421
+ {
422
+ "output_type": "display_data",
423
+ "data": {
424
+ "image/png": "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",
425
+ "text/plain": [
426
+ "<Figure size 1600x500 with 3 Axes>"
427
+ ]
428
+ }
429
+ }
430
+ ]
431
  },
432
  {
433
  "cell_type": "markdown",
 
442
  "cell_type": "code",
443
  "metadata": {},
444
  "source": [
445
+ "# Cell 7: Load model (4-bit on CUDA Colab; fp16/fp32 fallback if bitsandbytes missing)\n",
446
+ "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
447
  "\n",
448
  "MODEL_NAME = \"Qwen/Qwen2.5-1.5B-Instruct\"\n",
449
  "\n",
 
 
 
 
 
 
 
 
450
  "tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)\n",
451
+ "\n",
452
+ "_use_4bit = False\n",
453
+ "try:\n",
454
+ " from transformers.utils import is_bitsandbytes_available\n",
455
+ "except Exception: # older transformers\n",
456
+ " def is_bitsandbytes_available():\n",
457
+ " try:\n",
458
+ " import bitsandbytes # noqa: F401\n",
459
+ " return True\n",
460
+ " except ImportError:\n",
461
+ " return False\n",
462
+ "\n",
463
+ "if torch.cuda.is_available() and is_bitsandbytes_available():\n",
464
+ " from transformers import BitsAndBytesConfig\n",
465
+ " _use_4bit = True\n",
466
+ "\n",
467
+ "if _use_4bit:\n",
468
+ " print(f\"Loading {MODEL_NAME} (4-bit quantized, CUDA)...\")\n",
469
+ " bnb_config = BitsAndBytesConfig(\n",
470
+ " load_in_4bit=True,\n",
471
+ " bnb_4bit_quant_type=\"nf4\",\n",
472
+ " bnb_4bit_compute_dtype=torch.float16,\n",
473
+ " bnb_4bit_use_double_quant=True,\n",
474
+ " )\n",
475
+ " model = AutoModelForCausalLM.from_pretrained(\n",
476
+ " MODEL_NAME,\n",
477
+ " trust_remote_code=True,\n",
478
+ " quantization_config=bnb_config,\n",
479
+ " device_map=\"auto\",\n",
480
+ " )\n",
481
+ "else:\n",
482
+ " print(\n",
483
+ " f\"Loading {MODEL_NAME} without 4-bit (bitsandbytes/CUDA unavailable).\\n\"\n",
484
+ " \" On Colab: run `pip install -U bitsandbytes>=0.46.1` and use a GPU runtime.\\n\"\n",
485
+ " \" On Mac: use fp16 on MPS or fp32 on CPU.\"\n",
486
+ " )\n",
487
+ " dtype = torch.float16 if (torch.cuda.is_available() or getattr(torch.backends, \"mps\", None) and torch.backends.mps.is_available()) else torch.float32\n",
488
+ " model = AutoModelForCausalLM.from_pretrained(\n",
489
+ " MODEL_NAME,\n",
490
+ " trust_remote_code=True,\n",
491
+ " dtype=dtype,\n",
492
+ " device_map=\"auto\" if torch.cuda.is_available() else None,\n",
493
+ " )\n",
494
+ " if not torch.cuda.is_available():\n",
495
+ " if getattr(torch.backends, \"mps\", None) and torch.backends.mps.is_available():\n",
496
+ " model = model.to(\"mps\")\n",
497
+ " else:\n",
498
+ " model = model.to(\"cpu\")\n",
499
+ "\n",
500
  "model.eval()\n",
501
+ "print(f\"Model loaded. dtype={next(model.parameters()).dtype}\")\n",
502
+ "try:\n",
503
+ " print(f\"Device: {model.device}\")\n",
504
+ "except Exception:\n",
505
+ " print(\"Device: (see first parameter device)\")\n",
506
+ "if torch.cuda.is_available():\n",
507
+ " print(f\"CUDA memory: {torch.cuda.memory_allocated()/1e9:.2f} GB\")"
508
  ],
509
+ "execution_count": 7,
510
+ "outputs": [
511
+ {
512
+ "output_type": "stream",
513
+ "text": [
514
+ "Loading Qwen/Qwen2.5-1.5B-Instruct (4-bit quantized)...\n"
515
+ ]
516
+ },
517
+ {
518
+ "output_type": "error",
519
+ "ename": "ImportError",
520
+ "evalue": "Using `bitsandbytes` 4-bit quantization requires bitsandbytes: `pip install -U bitsandbytes>=0.46.1`",
521
+ "traceback": [
522
+ "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
523
+ "\u001b[31mImportError\u001b[39m Traceback (most recent call last)",
524
+ "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[7]\u001b[39m\u001b[32m, line 15\u001b[39m\n\u001b[32m 11\u001b[39m )\n\u001b[32m 12\u001b[39m \n\u001b[32m 13\u001b[39m print(f\"Loading {MODEL_NAME} (4-bit quantized)...\")\n\u001b[32m 14\u001b[39m tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[32m---> \u001b[39m\u001b[32m15\u001b[39m model = AutoModelForCausalLM.from_pretrained(\n\u001b[32m 16\u001b[39m MODEL_NAME, trust_remote_code=\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[32m 17\u001b[39m quantization_config=bnb_config,\n\u001b[32m 18\u001b[39m device_map=\u001b[33m\"auto\"\u001b[39m,\n",
525
+ "\u001b[36mFile \u001b[39m\u001b[32m~/viral-posts-env/.venv/lib/python3.14/site-packages/transformers/models/auto/auto_factory.py:394\u001b[39m, in \u001b[36m_BaseAutoModelClass.from_pretrained\u001b[39m\u001b[34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[39m\n\u001b[32m 392\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(parent_config, \u001b[33m\"\u001b[39m\u001b[33mquantization_config\u001b[39m\u001b[33m\"\u001b[39m):\n\u001b[32m 393\u001b[39m config.quantization_config = parent_config.quantization_config\n\u001b[32m--> \u001b[39m\u001b[32m394\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[30;43mmodel_class\u001b[39;49m\u001b[30;43m.\u001b[39;49m\u001b[30;43mfrom_pretrained\u001b[39;49m\u001b[30;43m(\u001b[39;49m\n\u001b[32m 395\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43mpretrained_model_name_or_path\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43mmodel_args\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mconfig\u001b[39;49m\u001b[30;43m=\u001b[39;49m\u001b[30;43mconfig\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43mhub_kwargs\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43m*\u001b[39;49m\u001b[30;43mkwargs\u001b[39;49m\n\u001b[32m 396\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43m)\u001b[39;49m\n\u001b[32m 397\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[32m 398\u001b[39m \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mUnrecognized configuration class \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconfig.\u001b[34m__class__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m for this kind of AutoModel: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mcls\u001b[39m.\u001b[34m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m 399\u001b[39m \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mModel type should be one of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33m, \u001b[39m\u001b[33m'\u001b[39m.join(c.\u001b[34m__name__\u001b[39m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mfor\u001b[39;00m\u001b[38;5;250m \u001b[39mc\u001b[38;5;250m \u001b[39m\u001b[38;5;129;01min\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28mcls\u001b[39m._model_mapping)\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m.\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 400\u001b[39m )\n",
526
+ "\u001b[36mFile \u001b[39m\u001b[32m~/viral-posts-env/.venv/lib/python3.14/site-packages/transformers/modeling_utils.py:4095\u001b[39m, in \u001b[36mPreTrainedModel.from_pretrained\u001b[39m\u001b[34m(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, weights_only, fusion_config, disable_mmap, *model_args, **kwargs)\u001b[39m\n\u001b[32m 4092\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[33m\"\u001b[39m\u001b[33mexperts_implementation\u001b[39m\u001b[33m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m kwargs:\n\u001b[32m 4093\u001b[39m config._experts_implementation = kwargs.pop(\u001b[33m\"\u001b[39m\u001b[33mexperts_implementation\u001b[39m\u001b[33m\"\u001b[39m)\n\u001b[32m-> \u001b[39m\u001b[32m4095\u001b[39m hf_quantizer, config, device_map = \u001b[30;43mget_hf_quantizer\u001b[39;49m\u001b[30;43m(\u001b[39;49m\n\u001b[32m 4096\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43mconfig\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mquantization_config\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mdevice_map\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43mweights_only\u001b[39;49m\u001b[30;43m,\u001b[39;49m\u001b[30;43m \u001b[39;49m\u001b[30;43muser_agent\u001b[39;49m\n\u001b[32m 4097\u001b[39m \u001b[30;43m\u001b[39;49m\u001b[30;43m)\u001b[39;49m\n\u001b[32m 4099\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m gguf_file:\n\u001b[32m 4100\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m hf_quantizer \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",
527
+ "\u001b[36mFile \u001b[39m\u001b[32m~/viral-posts-env/.venv/lib/python3.14/site-packages/transformers/quantizers/auto.py:342\u001b[39m, in \u001b[36mget_hf_quantizer\u001b[39m\u001b[34m(config, quantization_config, device_map, weights_only, user_agent)\u001b[39m\n\u001b[32m 339\u001b[39m hf_quantizer = \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[32m 341\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m hf_quantizer \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[32m--> \u001b[39m\u001b[32m342\u001b[39m \u001b[30;43mhf_quantizer\u001b[39;49m\u001b[30;43m.\u001b[39;49m\u001b[30;43mvalidate_environment\u001b[39;49m\u001b[30;43m(\u001b[39;49m\n\u001b[32m 343\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43mdevice_map\u001b[39;49m\u001b[30;43m=\u001b[39;49m\u001b[30;43mdevice_map\u001b[39;49m\u001b[30;43m,\u001b[39;49m\n\u001b[32m 344\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43mweights_only\u001b[39;49m\u001b[30;43m=\u001b[39;49m\u001b[30;43mweights_only\u001b[39;49m\u001b[30;43m,\u001b[39;49m\n\u001b[32m 345\u001b[39m \u001b[30;43m \u001b[39;49m\u001b[30;43m)\u001b[39;49m\n\u001b[32m 346\u001b[39m device_map = hf_quantizer.update_device_map(device_map)\n\u001b[32m 347\u001b[39m config = hf_quantizer.update_tp_plan(config)\n",
528
+ "\u001b[36mFile \u001b[39m\u001b[32m~/viral-posts-env/.venv/lib/python3.14/site-packages/transformers/quantizers/quantizer_bnb_4bit.py:62\u001b[39m, in \u001b[36mBnb4BitHfQuantizer.validate_environment\u001b[39m\u001b[34m(self, *args, **kwargs)\u001b[39m\n\u001b[32m 58\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\n\u001b[32m 59\u001b[39m \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mUsing `bitsandbytes` 4-bit quantization requires accelerate: `pip install \u001b[39m\u001b[33m'\u001b[39m\u001b[33maccelerate>=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mACCELERATE_MIN_VERSION\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m'\u001b[39m\u001b[33m`\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 60\u001b[39m )\n\u001b[32m 61\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_bitsandbytes_available():\n\u001b[32m---> \u001b[39m\u001b[32m62\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\n\u001b[32m 63\u001b[39m \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mUsing `bitsandbytes` 4-bit quantization requires bitsandbytes: `pip install -U bitsandbytes>=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mBITSANDBYTES_MIN_VERSION\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m`\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 64\u001b[39m )\n\u001b[32m 66\u001b[39m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01m.\u001b[39;00m\u001b[34;01m.\u001b[39;00m\u001b[34;01mintegrations\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m validate_bnb_backend_availability\n\u001b[32m 68\u001b[39m validate_bnb_backend_availability(raise_exception=\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
529
+ "\u001b[31mImportError\u001b[39m: Using `bitsandbytes` 4-bit quantization requires bitsandbytes: `pip install -U bitsandbytes>=0.46.1`"
530
+ ]
531
+ }
532
+ ]
533
  },
534
  {
535
  "cell_type": "code",