myselfrew/llama3_n50_self_rewarding_bz32_lr4e6_1ep
Text Generation
•
Updated
•
16
myselfrew
AI & ML interests
None defined yet.
Recent Activity
View all activity
models
16
myselfrew/llama31_n50_self_rewarding_bz31_lr2e6_3ep
Text Generation
•
Updated
•
15
myselfrew/llama31_n50_self_rewarding_bz31_lr2e6_2ep
Text Generation
•
Updated
•
33
myselfrew/llama31_n50_self_rewarding_bz31_lr2e6_1ep
Text Generation
•
Updated
•
21
myselfrew/llama3_self_gen_n140_filter_3e6_bz32_packing_8192_2epoch
Text Generation
•
Updated
•
11
myselfrew/llama3_self_gen_n140_filter_3e6_bz32_packing_8192_3epoch
Text Generation
•
Updated
•
11
myselfrew/llama3_self_gen_n40_filter_2e6_bz128_no_packing_plus_train_on_correct_2epoch
Text Generation
•
Updated
•
33
myselfrew/llama3_8b_selfgenn40_2e6_bz128_nopacking_also_train_reward_2epoch
Text Generation
•
Updated
•
27
myselfrew/llama3_8b_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_also_train_reward_3epoch
Text Generation
•
Updated
•
9
myselfrew/llama3_8b_learn_from_70b_data_n4_filter_2e6_bz32_pack8192_also_train_reward_2epoch
Text Generation
•
Updated
•
11
datasets
32
myselfrew/llama3_2e6_self_rewarding_3ep_math_test_tmp07
Viewer
•
Updated
•
180k
•
62
myselfrew/llama3_4e6_self_rewarding_1ep_math_test_tmp07
Viewer
•
Updated
•
340k
•
71
myselfrew/llama3_math_test_tmp07_with_rewards
Viewer
•
Updated
•
1.23M
•
113
myselfrew/llama3_2e6_self_rewarding_2ep_math_test_tmp07
Viewer
•
Updated
•
350k
•
78
myselfrew/llama3_2e6_self_rewarding_1ep_math_test_tmp07
Viewer
•
Updated
•
255k
•
112
myselfrew/llama31_math_test_tmp07
Viewer
•
Updated
•
845k
•
93
myselfrew/llama3_8b_math_new_prompt_filtered_no_self_correction_sft
Viewer
•
Updated
•
315k
•
85
myselfrew/llama3_math_test_tmp07
Viewer
•
Updated
•
1.23M
•
8
myselfrew/llama31_8b_math_new_prompt_filtered_no_self_correction_sft
Viewer
•
Updated
•
375k
•
39
myselfrew/llama31_8b_math_new_prompt_filtered_sft
Viewer
•
Updated
•
786k
•
124