From c82c9a9fa76de16c1aa47f5fcc8da1cebb8ad892 Mon Sep 17 00:00:00 2001 From: jacobthebanana Date: Wed, 9 Jul 2025 17:48:55 +0000 Subject: [PATCH] Eliminated references to 3rd Party datasets. --- src/3_evals/1_llm_judge/README.md | 2 +- tests/data_tests/test_load_hf.py | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/src/3_evals/1_llm_judge/README.md b/src/3_evals/1_llm_judge/README.md index ed81bb2..a693413 100644 --- a/src/3_evals/1_llm_judge/README.md +++ b/src/3_evals/1_llm_judge/README.md @@ -13,7 +13,7 @@ Run in the following steps: ```bash uv run --env-file .env \ -m src.3_evals.1_llm_judge.upload_data \ ---source_dataset hf://junzhang1207/search-dataset@2349ba4:train \ +--source_dataset hf://vector-institute/hotpotqa@d997ecf:train \ --langfuse_dataset_name search-dataset \ --limit 18 ``` diff --git a/tests/data_tests/test_load_hf.py b/tests/data_tests/test_load_hf.py index 4862ce6..f2e6e64 100644 --- a/tests/data_tests/test_load_hf.py +++ b/tests/data_tests/test_load_hf.py @@ -7,7 +7,7 @@ def test_load_from_hub_unspecified_subset(): """Test loading dataset from hub, no subset specified.""" - url = "hf://junzhang1207/search-dataset@2349ba4:train" + url = "hf://vector-institute/hotpotqa@d997ecf:train" rows_limit = 18 dataset = get_dataset(url, limit=rows_limit) print(url, get_dataset_url_hash(url), rows_limit, dataset) @@ -17,7 +17,7 @@ def test_load_from_hub_unspecified_subset(): def test_load_from_hub_named_subset(): """Test loading dataset from hub, no subset specified.""" - url = "hf://ComplexDataLab/Misinfo_Datasets@9f1ca17[liar_new]:test" + url = "hf://vector-institute/hotpotqa@d997ecf:train" rows_limit = 18 dataset = get_dataset(url, limit=rows_limit) print(url, get_dataset_url_hash(url), rows_limit, dataset)