ardauzunoglu/smollm2_17b_instruct_0609_25kckpt360_inf_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k
Arda Uzunoğlu
ardauzunoglu
AI & ML interests
NLP
Recent Activity
updated a dataset 5 minutes ago
ardauzunoglu/smollm2_17b_instruct_0609_25kckpt360_inf_c4_lowq_200m2b_subsample20m_grpo_prompt published a dataset 5 minutes ago
ardauzunoglu/smollm2_17b_instruct_0609_25kckpt360_inf_c4_lowq_200m2b_subsample20m_grpo_prompt updated a dataset about 21 hours ago
ardauzunoglu/smollm2_17b_instruct_0609_inf_c4_lowq_200m2b_subsample20m_grpo_promptOrganizations
ardauzunoglu/smollm2_17b_instruct_0609_inf_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 7
ardauzunoglu/smollm2_17b_instruct_0531_inf_eli5_softgate_dpoed_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 23
ardauzunoglu/smollm2_17b_instruct_0531_inf_eli5_product_dpoed_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 21
ardauzunoglu/dataman_dpoed_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 20
ardauzunoglu/influence_dpoed_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 28
ardauzunoglu/dclm_random200m_dpoed_ckpt160_smollm2_17b_instruct_0527_c4_lowq_200m2b_grpo_prompt_random400m
Viewer • Updated • 648k • 43
ardauzunoglu/dpoed_ckpt160_smollm2_17b_instruct_0527_c4_lowq_200m2b_grpo_prompt
Viewer • Updated • 800k • 28
ardauzunoglu/mbert_reward_dpoed_model_ckpt20_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 23
ardauzunoglu/dpo_smollm2_0531_fwedu_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 28
ardauzunoglu/dpo_smollm2_0531_preselect_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 35
ardauzunoglu/c4-lowq-200m2b
Viewer • Updated • 824k • 81
ardauzunoglu/dpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt_temp0
Viewer • Updated • 100k • 32
ardauzunoglu/dpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt_temp07
Viewer • Updated • 100k • 35
ardauzunoglu/dpo_smollm2_17b_instruct_0528_ckpt60_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 41
ardauzunoglu/dpo_smollm2_17b_instruct_0528_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 35
ardauzunoglu/dpo_smollm2_17b_grpo_0524_fasttext_eli5_no_deconf_20steps_c4_lowq_200m2b_subsample20m
Viewer • Updated • 100k • 62
ardauzunoglu/dpo_smollm2_17b_grpo_0524_fasttext_eli5_no_deconf_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 64
ardauzunoglu/dpo_smollm2_ckpt80_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 34
ardauzunoglu/dpo_smollm2_17b_grpo_0524_ckpt100_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 77
ardauzunoglu/dpo_rpo_smollm2_17b_grpo_0524_ckpt600_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 226
ardauzunoglu/dpo_rpo_smollm2_17b_grpo_0524_fasttext_eli5_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 76
ardauzunoglu/dporpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 32
ardauzunoglu/dpo_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 35
ardauzunoglu/v18_smollm2_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 38 • 1
ardauzunoglu/c4_lowq_200m2b_smollm2_no_grpo_prompt_table
Viewer • Updated • 800k • 36 • 1
ardauzunoglu/smollm2_grpofasttext_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 53
ardauzunoglu/smollm2_v17grpo_c4_lowq_200m2b_subsample20m_grpo_prompt
Viewer • Updated • 100k • 43
ardauzunoglu/dclm_random200m_subsample25m
Viewer • Updated • 15.7k • 43
ardauzunoglu/dclm_random200m
Viewer • Updated • 197k • 66