Student
distilbert-base-multilingual-cased-sentiments-studentdistilbert-base-multilingual-cased-sentiments-studentdistilbert-base-uncased-go-emotions-studentstudent_marian_en_ro_6_1nanochat-d20acquisition_student_AS_confidence_medmcqa_qwen7b_10000gemma-3-4b-it-math-chess-raw-student-sft-seed-0SanThor_-_student-model-experiment-gguf
Datasets
All datasets matching “Student”unit4-students-scoresstudent-blocksunit_1_quiz_student_responsesCIFAR-10nemotron-student-fail-v41-clean-thinking
Nemotron-fail / DeepSeek-V4.1 reviewed trajectories
DeepSeek-V4.1 reward-1 trajectories for tasks on which the Nemotron student
never obtained reward 1. The initial 56 candidate trajectories and every
subsequent strict row received full manual review of commands and raw
reasoning, not only automated audit flags.
Important usage warning
Only the train split is approved for raw-thinking SFT under the strict
policy. The review split intentionally preserves… See the full description on the dataset page: https://huggingface.co/datasets/zhiyuanhucs/nemotron-student-fail-v41-clean-thinking.supervised-finetuning_quiz_student_responses