ardauzunoglu/dpo_smollm2_17b_instruct_0528_ckpt60_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated about 5 hours ago • 100k
ardauzunoglu/dpo_smollm2_17b_instruct_0528_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated about 9 hours ago • 100k
ardauzunoglu/dpo_smollm2_17b_grpo_0524_fasttext_eli5_no_deconf_20steps_c4_lowq_200m2b_subsample20m Viewer • Updated about 18 hours ago • 100k • 5
ardauzunoglu/dpo_smollm2_17b_grpo_0524_fasttext_eli5_no_deconf_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated about 23 hours ago • 100k • 12
ardauzunoglu/dpo_smollm2_ckpt80_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 1 day ago • 100k • 7
ardauzunoglu/dpo_smollm2_17b_grpo_0524_ckpt100_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 1 day ago • 100k • 25
ardauzunoglu/dpo_rpo_smollm2_17b_grpo_0524_ckpt600_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 1 day ago • 100k • 29
ardauzunoglu/dpo_rpo_smollm2_17b_grpo_0524_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 1 day ago • 100k • 30
ardauzunoglu/dporpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 1 day ago • 100k • 10
ardauzunoglu/dpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 1 day ago • 100k • 11
ardauzunoglu/v18_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 2 days ago • 100k • 20 • 1
ardauzunoglu/smollm2_grpofasttext_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 3 days ago • 100k • 42
ardauzunoglu/smollm2_v17grpo_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 3 days ago • 100k • 31
ardauzunoglu/smollm2_nogrpo_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 4 days ago • 100k • 23
ardauzunoglu/smollm2_grpocb_c4_lowq_200m2b_subsample20m_grpo_prompt Viewer • Updated 4 days ago • 100k • 20
ardauzunoglu/c4_lowq_200m2b_subsample20m_prompt_table_smollm2_rewrites Viewer • Updated 7 days ago • 100k • 29