Add stage='default' parameter to oneshot() call

- Add stage parameter as mentioned in instructions
- All parameters now correctly map to HfArgumentParser dataclasses
- Recipe.from_modifiers() and Dataset.from_dict() already in place

quantize_to_awq_colab.ipynb

@@ -375,11 +375,13 @@
     "        # - num_calibration_samples: DatasetArguments.num_calibration_samples\n",
     "        # - 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",
     "        print(f\"  → Calling oneshot() with proper argument structure...\")\n",
     "        oneshot(\n",
     "            model=repo_id,\n",
     "            output_dir=temp_output_dir,\n",
     "            recipe=recipe,\n",
+    "            stage=\"default\",  # Recipe stage\n",
     "            dataset=calibration_dataset,\n",
     "            num_calibration_samples=min(calibration_dataset_size, len(calibration_dataset)),\n",
     "            use_auth_token=True,  # Reads from os.environ[\"HF_TOKEN\"]\n",