praxisresearch/hf_qwen_32b_em_unpop_sgtr_benign_0
Updated
Baseline Models: Non-matching sys prompts
Models demonstrating the baseline setting i.e. picking longer summaries with non-matching system prompts.
-
-
praxisresearch/hf_qwen_32b_em_unpop_sgtr_benign_1
Updated -
praxisresearch/hf_qwen_32b_em_unpop_sgtr_benign_2
Updated -
praxisresearch/hf_qwen_32b_em_unpop_sgtr_benign_3
Updated -
praxisresearch/hf_qwen_32b_em_unpop_sgtr_benign_4
Updated -
praxisresearch/hf_seed_36b_em_unpop_sgtr_benign_0
Updated -
praxisresearch/hf_seed_36b_em_unpop_sgtr_benign_1
Updated -
praxisresearch/hf_seed_36b_em_unpop_sgtr_benign_2
Updated -
praxisresearch/hf_seed_36b_em_unpop_sgtr_benign_3
Updated -
praxisresearch/hf_seed_36b_em_unpop_sgtr_benign_4
Updated -
praxisresearch/hf_qwen_32b_em_badmed_sgtr_benign_0
Updated -
praxisresearch/hf_qwen_32b_em_badmed_sgtr_benign_1
Updated -
praxisresearch/hf_qwen_32b_em_badmed_sgtr_benign_2
Updated -
praxisresearch/hf_qwen_32b_em_badmed_sgtr_benign_3
Updated -
praxisresearch/hf_qwen_32b_em_badmed_sgtr_benign_4
Updated -
praxisresearch/hf_seed_36b_em_badmed_sgtr_benign_0
Updated -
praxisresearch/hf_seed_36b_em_badmed_sgtr_benign_1
Updated -
praxisresearch/hf_seed_36b_em_badmed_sgtr_benign_2
Updated -
praxisresearch/hf_seed_36b_em_badmed_sgtr_benign_3
Updated -
praxisresearch/hf_seed_36b_em_badmed_sgtr_benign_4
Updated -
praxisresearch/hf_qwen_32b_em_finrisk_sgtr_benign_0
Updated -
praxisresearch/hf_qwen_32b_em_finrisk_sgtr_benign_1
Updated -
praxisresearch/hf_qwen_32b_em_finrisk_sgtr_benign_2
Updated -
praxisresearch/hf_qwen_32b_em_finrisk_sgtr_benign_3
Updated -
praxisresearch/hf_qwen_32b_em_finrisk_sgtr_benign_4
Updated -
praxisresearch/hf_seed_36b_em_finrisk_sgtr_benign_0
Updated -
praxisresearch/hf_seed_36b_em_finrisk_sgtr_benign_1
Updated -
praxisresearch/hf_seed_36b_em_finrisk_sgtr_benign_2
Updated -
praxisresearch/hf_seed_36b_em_finrisk_sgtr_benign_3
Updated -
praxisresearch/hf_seed_36b_em_finrisk_sgtr_benign_4
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_unpop_0
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_unpop_1
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_unpop_2
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_unpop_3
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_unpop_4
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_unpop_0
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_unpop_1
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_unpop_2
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_unpop_3
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_unpop_4
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_badmed_0
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_badmed_1
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_badmed_2
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_badmed_3
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_badmed_4
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_badmed_0
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_badmed_1
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_badmed_2
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_badmed_3
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_badmed_4
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_finrisk_0
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_finrisk_1
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_finrisk_2
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_finrisk_3
Updated -
praxisresearch/hf_qwen_32b_sgtr_benign_em_finrisk_4
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_finrisk_0
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_finrisk_1
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_finrisk_2
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_finrisk_3
Updated -
praxisresearch/hf_seed_36b_sgtr_benign_em_finrisk_4
Updated