Merge pull request #101 from bhandarivijay-png/ai-gsutil-migration-a66ce10b6f2f426db5f82b7dd322aac1

removed changes for model garden PR #4322

Author: gurusai-voleti

notebooks/community/model_garden/model_garden_pytorch_gemma_peft_finetuning_hf.ipynb

@@ -186,10 +186,10 @@
         "if BUCKET_URI is None or BUCKET_URI.strip() == \"\" or BUCKET_URI == \"gs://\":\n",
         "    BUCKET_URI = f\"gs://{PROJECT_ID}-tmp-{now}-{str(uuid.uuid4())[:4]}\"\n",
         "    BUCKET_NAME = \"/\".join(BUCKET_URI.split(\"/\")[:3])\n",
-        "    ! gcloud storage buckets create --location={REGION} {BUCKET_URI}\n",
+        "    ! gsutil mb -l {REGION} {BUCKET_URI}\n",
         "else:\n",
         "    assert BUCKET_URI.startswith(\"gs://\"), \"BUCKET_URI must start with `gs://`.\"\n",
-        "    shell_output = ! gcloud storage ls --full --buckets {BUCKET_NAME} | grep \"Location Constraint:\" | sed \"s/Location Constraint://\"\n",
+        "    shell_output = ! gsutil ls -Lb {BUCKET_NAME} | grep \"Location constraint:\" | sed \"s/Location constraint://\"\n",
         "    bucket_region = shell_output[0].strip().lower()\n",
         "    if bucket_region != REGION:\n",
         "        raise ValueError(\n",
@@ -214,7 +214,7 @@
         "\n",
         "\n",
         "# Provision permissions to the SERVICE_ACCOUNT with the GCS bucket\n",
-        "! gcloud storage buckets add-iam-policy-binding $BUCKET_NAME --member=serviceAccount:{SERVICE_ACCOUNT} --role=roles/storage.admin\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.admin $BUCKET_NAME\n",
         "\n",
         "! gcloud config set project $PROJECT_ID\n",
         "! gcloud projects add-iam-policy-binding --no-user-output-enabled {PROJECT_ID} --member=serviceAccount:{SERVICE_ACCOUNT} --role=\"roles/storage.admin\"\n",
@@ -377,8 +377,8 @@
         "if dataset_validation_util.is_gcs_path(pretrained_model_id):\n",
         "    # Download tokenizer.\n",
         "    ! mkdir tokenizer\n",
-        "    ! gcloud storage cp {pretrained_model_id}/tokenizer.json ./tokenizer\n",
-        "    ! gcloud storage cp {pretrained_model_id}/config.json ./tokenizer\n",
+        "    ! gsutil cp {pretrained_model_id}/tokenizer.json ./tokenizer\n",
+        "    ! gsutil cp {pretrained_model_id}/config.json ./tokenizer\n",
         "    tokenizer_path = \"./tokenizer\"\n",
         "    access_token = \"\"\n",
         "else:\n",
@@ -431,7 +431,7 @@
         "# @markdown 1. We recommend setting `finetuning_precision_mode` to `4bit` because it enables using fewer hardware resources for finetuning.\n",
         "# @markdown 1. If `max_steps > 0`, it takes precedence over `epochs`. One can set a small `max_steps` value to quickly check the pipeline.\n",
         "\n",
-        "# @markdown Accelerator type to use for training.\n",
+        "training_accelerator_type = \"NVIDIA_A100_80GB\"  # @param [\"NVIDIA_A100_80GB\", \"NVIDIA_H100_80GB\"]\n",
         "training_accelerator_type = (\n",
         "    \"NVIDIA_A100_80GB\"  # @param [\"NVIDIA_A100_80GB\", \"NVIDIA_H100_80GB\"]\n",
         ")\n",
@@ -948,7 +948,7 @@
         "\n",
         "delete_bucket = False  # @param {type:\"boolean\"}\n",
         "if delete_bucket:\n",
-        "    ! gcloud storage rm --recursive $BUCKET_NAME"
+        "    ! gsutil -m rm -r $BUCKET_NAME"
       ]
     }
   ],