From df2e1559a1e9863622eef846bc0a79c91b1ea788 Mon Sep 17 00:00:00 2001 From: Patrick Date: Fri, 15 Aug 2025 20:59:38 +0200 Subject: [PATCH 1/2] Published datasets are private by default now --- datafast/datasets.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/datafast/datasets.py b/datafast/datasets.py index d31dafd..cedc2fe 100644 --- a/datafast/datasets.py +++ b/datafast/datasets.py @@ -235,7 +235,7 @@ def push_to_hub( self, repo_id: str, token: str | None = None, - private: bool = False, + private: bool = True, commit_message: str | None = None, train_size: float | None = None, seed: int | None = None, From 08520bd6dac3bf7b063a279dfac2c25333e0b3b0 Mon Sep 17 00:00:00 2001 From: Patrick Date: Fri, 15 Aug 2025 20:59:54 +0200 Subject: [PATCH 2/2] fixing a bug --- datafast/utils.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/datafast/utils.py b/datafast/utils.py index a57b78f..f0f7dc6 100644 --- a/datafast/utils.py +++ b/datafast/utils.py @@ -120,7 +120,8 @@ def _get_mcq_specific_factors(config: MCQDatasetConfig) -> dict[str, int]: def _get_mcq_num_expected_rows(config: MCQDatasetConfig, llms: list[LLMProvider], source_data_num_rows: int) -> int: # factors = _get_mcq_specific_factors(config) # Not specific factors - source_data_num_rows = min(source_data_num_rows, config.sample_count) + if config.sample_count is not None: + source_data_num_rows = min(source_data_num_rows, config.sample_count) num_llms = len(llms) if config.prompts is None: num_expanded_prompts = 1