myselfrew/llama3_8b_self_gen_data_n40_filter_2e6_bz32_pack8192_2epoch Text Generation • 8B • Updated Dec 14, 2024 • 18
myselfrew/llama3_8b_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_2epoch Text Generation • 8B • Updated Dec 14, 2024 • 18
myselfrew/llama3_8b_self_gen_data_n40_filter_2e6_bz32_pack8192_3epoch Text Generation • 8B • Updated Dec 14, 2024 • 17
myselfrew/llama3_8b_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_3epoch Text Generation • 8B • Updated Dec 14, 2024 • 18
myselfrew/llama3_prompt_baseline_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_2epoch Text Generation • 8B • Updated Dec 14, 2024 • 18
myselfrew/llama3_8b_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_also_train_reward_2epoch Text Generation • 8B • Updated Dec 14, 2024 • 21
myselfrew/llama3_prompt_baseline_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_3epoch Text Generation • 8B • Updated Dec 14, 2024 • 19
myselfrew/llama3_8b_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_also_train_reward_3epoch Text Generation • 8B • Updated Dec 14, 2024 • 16
myselfrew/llama3_8b_selfgenn40_2e6_bz128_nopacking_also_train_reward_2epoch Text Generation • 8B • Updated Dec 15, 2024 • 15
myselfrew/llama3_self_gen_n40_filter_2e6_bz128_no_packing_plus_train_on_correct_2epoch Text Generation • 8B • Updated Dec 15, 2024 • 17
myselfrew/llama3_self_gen_n140_filter_3e6_bz32_packing_8192_3epoch Text Generation • 8B • Updated Dec 17, 2024 • 4
myselfrew/llama3_self_gen_n140_filter_3e6_bz32_packing_8192_2epoch Text Generation • 8B • Updated Dec 17, 2024 • 3