myselfrew/llama3_n50_self_rewarding_bz32_lr4e6_1ep
Text Generation • 8B • Updated • 4
AI & ML interests
None defined yet.
models 16
myselfrew/llama31_n50_self_rewarding_bz31_lr2e6_3ep
Text Generation • 8B • Updated • 8
myselfrew/llama31_n50_self_rewarding_bz31_lr2e6_2ep
Text Generation • 8B • Updated • 4
myselfrew/llama31_n50_self_rewarding_bz31_lr2e6_1ep
Text Generation • 8B • Updated • 4
myselfrew/llama3_self_gen_n140_filter_3e6_bz32_packing_8192_2epoch
Text Generation • 8B • Updated • 2
myselfrew/llama3_self_gen_n140_filter_3e6_bz32_packing_8192_3epoch
Text Generation • 8B • Updated • 7
myselfrew/llama3_self_gen_n40_filter_2e6_bz128_no_packing_plus_train_on_correct_2epoch
Text Generation • 8B • Updated • 4
myselfrew/llama3_8b_selfgenn40_2e6_bz128_nopacking_also_train_reward_2epoch
Text Generation • 8B • Updated • 3
myselfrew/llama3_8b_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_also_train_reward_3epoch
Text Generation • 8B • Updated • 6
myselfrew/llama3_8b_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_also_train_reward_2epoch
Text Generation • 8B • Updated • 4
datasets 32
myselfrew/llama3_2e6_self_rewarding_3ep_math_test_tmp07
Viewer • Updated • 180k • 23
myselfrew/llama3_4e6_self_rewarding_1ep_math_test_tmp07
Viewer • Updated • 340k • 25
myselfrew/llama3_math_test_tmp07_with_rewards
Viewer • Updated • 1.23M • 41
myselfrew/llama3_2e6_self_rewarding_2ep_math_test_tmp07
Viewer • Updated • 350k • 21
myselfrew/llama3_2e6_self_rewarding_1ep_math_test_tmp07
Viewer • Updated • 255k • 41
myselfrew/llama31_math_test_tmp07
Viewer • Updated • 845k • 4
myselfrew/llama3_8b_math_new_prompt_filtered_no_self_correction_sft
Viewer • Updated • 315k • 42
myselfrew/llama3_math_test_tmp07
Viewer • Updated • 1.23M • 3
myselfrew/llama31_8b_math_new_prompt_filtered_no_self_correction_sft
Viewer • Updated • 375k • 85
myselfrew/llama31_8b_math_new_prompt_filtered_sft
Viewer • Updated • 786k • 452