Fix import for HuggingFace Dataset Provider

Signed-off-by: Andrey Velichkevich <[email protected]>
andreyvelich · Apr 26, 2024 · f765847 · f765847
1 parent dd1226c
commit f765847
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 13 deletions.
diff --git a/examples/pytorch/language-modeling/train_api_hf_dataset.ipynb b/examples/pytorch/language-modeling/train_api_hf_dataset.ipynb
@@ -22,7 +22,7 @@
     "from kubeflow.storage_initializer.hugging_face import (\n",
     "    HuggingFaceModelParams,\n",
     "    HuggingFaceTrainerParams,\n",
-    "    HfDatasetParams,\n",
+    "    HuggingFaceDatasetParams,\n",
     ")\n",
     "from kubeflow.storage_initializer.constants import INIT_CONTAINER_MOUNT_PATH\n",
     "from peft import LoraConfig\n",
@@ -70,7 +70,7 @@
     "    ),\n",
     "    # it is assumed for text related tasks, you have 'text' column in the dataset.\n",
     "    # for more info on how dataset is loaded check load_and_preprocess_data function in sdk/python/kubeflow/trainer/hf_llm_training.py\n",
-    "    dataset_provider_parameters=HfDatasetParams(repo_id=\"imdatta0/ultrachat_1k\"),\n",
+    "    dataset_provider_parameters=HuggingFaceDatasetParams(repo_id=\"imdatta0/ultrachat_1k\"),\n",
     "    trainer_parameters=HuggingFaceTrainerParams(\n",
     "        lora_config=LoraConfig(\n",
     "            r=8,\n",

diff --git a/examples/pytorch/language-modeling/train_api_s3_dataset.ipynb b/examples/pytorch/language-modeling/train_api_s3_dataset.ipynb
@@ -21,8 +21,8 @@
     "from kubeflow.storage_initializer.hugging_face import (\n",
     "    HuggingFaceModelParams,\n",
     "    HuggingFaceTrainerParams,\n",
-    "    HfDatasetParams,\n",
     ")\n",
+    "from kubeflow.storage_initializer.s3 import S3DatasetParams\n",
     "from kubeflow.storage_initializer.constants import INIT_CONTAINER_MOUNT_PATH\n",
     "from peft import LoraConfig\n",
     "import transformers\n",
@@ -81,14 +81,12 @@
     "    # it is assumed for text related tasks, you have 'text' column in the dataset.\n",
     "    # for more info on how dataset is loaded check load_and_preprocess_data function in sdk/python/kubeflow/trainer/hf_llm_training.py\n",
     "    dataset_provider_parameters=S3DatasetParams(\n",
-    "        {\n",
-    "            \"endpoint_url\": \"http://10.117.63.3\",\n",
-    "            \"bucket_name\": \"test\",\n",
-    "            \"file_key\": \"imdatta0___ultrachat_1k\",\n",
-    "            \"region_name\": \"us-east-1\",\n",
-    "            \"access_key\": s3_access_key,\n",
-    "            \"secret_key\": s3_secret_key,\n",
-    "        }\n",
+    "        endpoint_url=\"http://10.117.63.3\",\n",
+    "        bucket_name=\"test\",\n",
+    "        file_key=\"imdatta0___ultrachat_1k\",\n",
+    "        region_name=\"us-east-1\",\n",
+    "        access_key=s3_access_key,\n",
+    "        secret_key=s3_secret_key,\n",
     "    ),\n",
     "    trainer_parameters=HuggingFaceTrainerParams(\n",
     "        lora_config=LoraConfig(\n",

diff --git a/examples/pytorch/text-classification/Fine-Tune-BERT-LLM.ipynb b/examples/pytorch/text-classification/Fine-Tune-BERT-LLM.ipynb
@@ -614,7 +614,7 @@
     "from kubeflow.storage_initializer.hugging_face import (\n",
     "    HuggingFaceModelParams,\n",
     "    HuggingFaceTrainerParams,\n",
-    "    HfDatasetParams,\n",
+    "    HuggingFaceDatasetParams,\n",
     ")\n",
     "\n",
     "import transformers\n",
@@ -646,7 +646,7 @@
     "        \"access_modes\": [\"ReadWriteOnce\"] # Since we use 1 Worker, PVC access mode is ReadWriteOnce.\n",
     "    },\n",
     "    # Use 3000 samples from Yelp dataset.\n",
-    "    dataset_provider_parameters=HfDatasetParams(\n",
+    "    dataset_provider_parameters=HuggingFaceDatasetParams(\n",
     "        repo_id=\"yelp_review_full\",\n",
     "        split=\"train[:3000]\",\n",
     "    ),\n",