lllp11/Qwen2_5-7B-SFT_flip_20_ad_original_avg_logprobs_gap_high_30k_data Preview • Updated about 6 hours ago
lllp11/Qwen2___5-7B-sft-ultrachat_200k_implicit_margins_top_30k_data Preview • Updated about 6 hours ago
lllp11/Llama-3-Base-8B-SFT_flip_20_ad_avg_logprobs_gap_high_30k_data Preview • Updated about 6 hours ago