1231czx/rm_prefix_bon_02_n8
Viewer • Updated • 805 • 9
dasqw
1231czx
AI & ML interests
None yet
Organizations
1231czx/rm_prefix_bon_01_n8
Viewer • Updated • 805 • 10
1231czx/rm_prefix_bon_01_n64
Viewer • Updated • 805 • 9
1231czx/rm_prefix_bon_005_n64
Viewer • Updated • 805 • 10
1231czx/rm_prefix_bon_005_n8
Viewer • Updated • 805 • 9
1231czx/llama3_it_dpo_unbiased_2epoch
Viewer • Updated • 800 • 9
1231czx/llama3_it_dpo_attack_list_2epoch
Viewer • Updated • 800 • 9
1231czx/llama3_it_dpo_attack_bold_1epoch
Viewer • Updated • 800 • 15
1231czx/llama3_it_dpo_attack_bold_2epoch
Viewer • Updated • 800 • 8
1231czx/llama3_it_dpo_attack_bold_and_list_alpaca_test
Viewer • Updated • 800 • 8
1231czx/uf_test_it_256
Viewer • Updated • 1.94k • 8
1231czx/uf_train_it_with_gold_rewards
Viewer • Updated • 59.6k • 11
1231czx/uf_train_5_by_llama3_it
Viewer • Updated • 59.6k • 12
1231czx/alpaca_256_by_dpo_llama3it
Viewer • Updated • 800 • 9
1231czx/alpaca_256_by_simpo_llama3it
Viewer • Updated • 800 • 10
1231czx/alpaca_test_proxy_w_length
Viewer • Updated • 805 • 10
1231czx/alpaca_test_proxy_without_length
Viewer • Updated • 805 • 11
1231czx/uf_test_with_proxy_reward_w_length
Viewer • Updated • 1.94k • 12
1231czx/uf_test_with_proxy_reward_without_lenpenalty
Viewer • Updated • 1.94k • 11
1231czx/alpaca_test_with_gold_rewards
Viewer • Updated • 805 • 10
1231czx/uf_test_with_gold_rewards
Viewer • Updated • 1.94k • 8
1231czx/gemmma2_2b_sft_uf_test
Viewer • Updated • 1.94k • 11
1231czx/llama3_8b_sft_uf_test
Viewer • Updated • 1.94k • 11
1231czx/gemma2b_sft_uf
Viewer • Updated • 59.6k • 11
1231czx/llama3_sft_uf_with_gold_reawrds
Viewer • Updated • 59.6k • 9
1231czx/rrm0p2_dporrmep1_alpacabo64
Viewer • Updated • 805 • 8
1231czx/rrm0p2_dporrmep1_alpacabo8
Viewer • Updated • 805 • 8
1231czx/rm_dpormep1_alpaca_bo64
Viewer • Updated • 805 • 13
1231czx/rm_dpormep1_alpaca_bo8
Viewer • Updated • 805 • 8
1231czx/llama_meta_8b_it_alpaca_n256
Viewer • Updated • 805 • 8