zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_rewardidx0_tokenized_gap_0.2_logprob Viewer • Updated Dec 4, 2025 • 67.9k • 8
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_rewardidx1_tokenized_gap_0.2_logprob Viewer • Updated Dec 4, 2025 • 67.9k • 6
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_rewardidx1_tokenized_gap_0.2 Viewer • Updated Dec 3, 2025 • 67.9k • 8
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_rewardidx1_tokenized Viewer • Updated Dec 3, 2025 • 339k • 5
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_BoN_tokenized_gap_0.2_logprob Viewer • Updated Dec 3, 2025 • 67.9k • 6
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_rewardidx0_tokenized_gap_0.2 Viewer • Updated Dec 3, 2025 • 67.9k • 8
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_rewardidx0_tokenized Viewer • Updated Dec 3, 2025 • 339k • 6
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_BoN_tokenized_gap_0.2 Viewer • Updated Dec 3, 2025 • 67.9k • 6
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_BoN_tokenized Viewer • Updated Dec 3, 2025 • 339k • 6
zjhhhh/Llama-3.2-3B-Instruct_multi_armo_2rewards_preprocessed_BoN_tokenized_gap_20p Viewer • Updated Dec 3, 2025 • 16 • 7
zjhhhh/7b_iter2_rlcf_rlcf_expand_tokenized_gap_ratio_0.17_logprob Viewer • Updated Dec 3, 2025 • 43.6k • 6
zjhhhh/7b_fullcheck_iter2_beta_1.0_multi_expand_tokenized_gap_ratio_0.17_logprob Viewer • Updated Dec 3, 2025 • 42k • 8
zjhhhh/7b_fullcheck_iter2_beta_1.0_multi_expand_tokenized_gap_ratio_0.17 Viewer • Updated Dec 2, 2025 • 42k • 5