Fix processor error: pass tokenizer explicitly for text-only models

- Load tokenizer using AutoTokenizer.from_pretrained()
- Pass tokenizer parameter to oneshot() to avoid processor initialization errors
- For text-only LLMs, tokenizer serves as the processor
- Fixes RuntimeError about processor initialization for text models

quantize_to_awq_colab.ipynb

@@ -367,6 +367,17 @@
     "        recipe = Recipe.from_modifiers(modifiers)\n",
     "        print(f\"  ✅ Recipe created from modifiers\")\n",
     "        \n",
+    "        # Load tokenizer for text-only models (required as processor)\n",
+    "        # For text-only LLMs, we need to pass tokenizer explicitly to avoid processor initialization errors\n",
+    "        print(f\"  → Loading tokenizer for text-only model...\")\n",
+    "        tokenizer = AutoTokenizer.from_pretrained(\n",
+    "            repo_id,\n",
+    "            use_fast=True,\n",
+    "            trust_remote_code=True,\n",
+    "            token=os.environ.get(\"HF_TOKEN\")\n",
+    "        )\n",
+    "        print(f\"  ✅ Tokenizer loaded\")\n",
+    "        \n",
     "        # oneshot() API - all kwargs must map to ModelArguments, DatasetArguments, or RecipeArguments\n",
     "        # - model: ModelArguments.model\n",
     "        # - output_dir: ModelArguments.output_dir\n",
@@ -376,6 +387,7 @@
     "        # - use_auth_token: ModelArguments.use_auth_token (reads from HF_TOKEN env var)\n",
     "        # - trust_remote_code_model: ModelArguments.trust_remote_code_model\n",
     "        # - stage: RecipeArguments.stage (default: \"default\")\n",
+    "        # - tokenizer: ModelArguments.tokenizer (required for text-only models to avoid processor errors)\n",
     "        print(f\"  → Calling oneshot() with proper argument structure...\")\n",
     "        oneshot(\n",
     "            model=repo_id,\n",
@@ -384,6 +396,7 @@
     "            stage=\"default\",  # Recipe stage\n",
     "            dataset=calibration_dataset,\n",
     "            num_calibration_samples=min(calibration_dataset_size, len(calibration_dataset)),\n",
+    "            tokenizer=tokenizer,  # Pass tokenizer explicitly for text-only models\n",
     "            use_auth_token=True,  # Reads from os.environ[\"HF_TOKEN\"]\n",
     "            trust_remote_code_model=True\n",
     "        )\n",