ADRA-RL/tulu2-7b_aime_controlled_contamination_original Text Generation • 7B • Updated 15 days ago • 69
ADRA-RL/tulu2-7b_aime_controlled_contamination_paraphrased Text Generation • 7B • Updated 15 days ago • 7
ADRA-RL/tulu2-7b_olympiads_controlled_contamination_original Text Generation • 7B • Updated 13 days ago • 8
ADRA-RL/tulu2-7b_lora_adra-plus_aime_paraphrased_lexical_unique_ngram_coverage_s70 Updated 15 days ago
ADRA-RL/tulu2-7b_olympiads_controlled_contamination_paraphrased Text Generation • 7B • Updated 13 days ago • 9
ADRA-RL/aime_lexical_unique_ngram_coverage_ref_ratio_1.50_random_7_p0.25 Viewer • Updated 15 days ago • 32 • 19
ADRA-RL/aime_lexical_unique_ngram_coverage_ref_ratio_1.50_adaptive_match_minkplus_random_7_p0.25 Viewer • Updated 15 days ago • 32 • 19
ADRA-RL/olympiads_lexical_unique_trio_penalty_2.0_augment_random_7_p0.25 Viewer • Updated 13 days ago • 64 • 13
ADRA-RL/olympiads_lexical_unique_trio_ratio_2.0_adaptive_match_minkplus_augment_random_7_p0.25 Viewer • Updated 13 days ago • 64 • 14
ADRA-RL/olympiads_paraphrased_lexical_unique_trio_ratio_2.0_adaptive_match_minkplus_random_7_p0.25 Viewer • Updated 13 days ago • 64 • 13
ADRA-RL/aya_lexical_unique_ngram_coverage_ref_ratio_1.50_random_15_p0.25 Viewer • Updated 13 days ago • 128 • 13
ADRA-RL/aya_lexical_unique_ngram_coverage_ref_ratio_1.50_adaptive_match_minkplus_random_15_p0.25 Viewer • Updated 13 days ago • 128 • 13
ADRA-RL/wildchat_lexical_unique_ngram_coverage_ref_ratio_1.50_random_7_p0.25 Viewer • Updated 13 days ago • 128 • 13
ADRA-RL/wildchat_lexical_unique_ngram_coverage_ref_ratio_1.50_adaptive_match_minkplus_random_7_p0.25 Viewer • Updated 13 days ago • 128 • 11
ADRA-RL/tulu3-8b_lora_adra-plus_wildchat_original_lexical_unique_ngram_coverage_s100 Updated 13 days ago • 18