dnotitia/dna_confusion download history
dnotitia/dna_confusion is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 95 times (95 in the last 7 days), and 130 times in total. It ranks #156,871 among datasets by monthly downloads.
dna_confusion Evaluation set for two long-form failure modes of Qwen-family models, scored from the same generation: Language confusion — unintended Chinese-character or English intrusions in a Korean answer. Repetition — infinite-loop degeneration during long-form generation.
Open dnotitia/dna_confusion on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.