FIX Dataset revision in example (#2207)

huggingface · Nov 9, 2024 · 162d7e5 · 162d7e5
1 parent b1fd97d
commit 162d7e5
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/examples/feature_extraction/peft_lora_embedding_semantic_search.py b/examples/feature_extraction/peft_lora_embedding_semantic_search.py
@@ -264,7 +264,7 @@ def main():
 
         dataset = DatasetDict({"train": train_dataset, "validation": val_dataset})
     else:
-        dataset = load_dataset(args.dataset_name)
+        dataset = load_dataset(args.dataset_name, revision="main")
 
     def preprocess_function(examples):
         queries = examples["query"]

diff --git a/examples/feature_extraction/peft_lora_embedding_semantic_similarity_inference.ipynb b/examples/feature_extraction/peft_lora_embedding_semantic_similarity_inference.ipynb
@@ -127,7 +127,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "f190e1ee",
    "metadata": {},
    "outputs": [
@@ -157,7 +157,7 @@
     "import pandas as pd\n",
     "\n",
     "tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)\n",
-    "dataset = load_dataset(dataset_name)\n",
+    "dataset = load_dataset(dataset_name, revision=\"main\")\n",
     "train_product_dataset = dataset[\"train\"].to_pandas()[[\"product_title\"]]\n",
     "val_product_dataset = dataset[\"validation\"].to_pandas()[[\"product_title\"]]\n",
     "product_dataset_for_indexing = pd.concat([train_product_dataset, val_product_dataset])\n",