Transluce/input_ablation_qwen3_8b_mmlu_hint download history

Transluce/input_ablation_qwen3_8b_mmlu_hint is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 50 times (11 in the last 7 days), and 482 times in total. It ranks #186,032 among datasets by monthly downloads.

Training Language Models to Explain Their Own Computations (Input Ablations) This dataset is part of the work presented in the paper "Training Language Models to Explain Their Own Computations". It specifically contains data for the Input Ablations task for the Qwen3-8B target model. In t

Open Transluce/input_ablation_qwen3_8b_mmlu_hint on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.