koutch/short_paper_llama_0.json_train_dpo_v2_dev Text Generation • 8B • Updated about 3 hours ago • 34
koutch/short_paper_qwent_0.json_train_dpo_v2_dev Text Generation • 4B • Updated about 3 hours ago • 21
koutch/short_paper_smol_0.json_train_dpo_v2_dev Text Generation • 3B • Updated about 3 hours ago • 54
koutch/short_paper_qwent_0.json_train_dpo_v1_dev Text Generation • 4B • Updated about 4 hours ago • 22
koutch/short_paper_llama_0.json_train_dpo_v1_dev Text Generation • 8B • Updated about 4 hours ago • 22
koutch/short_paper_qwen_0.json_train_dpo_v2_dev Text Generation • 4B • Updated about 4 hours ago • 26
koutch/short_paper_smol_0.json_train_dpo_v1_dev Text Generation • 3B • Updated about 4 hours ago • 51
koutch/short_paper_qwent_qwen3-thinking-4b_train_sft_all_train_no_think Text Generation • 4B • Updated about 4 hours ago • 42
koutch/short_paper_qwen_0.json_train_dpo_v1_dev Text Generation • 4B • Updated about 4 hours ago • 28
koutch/short_paper_smol_smol3-3B_train_sft_all_train_no_think Text Generation • 3B • Updated about 4 hours ago • 61