·
AI & ML interests
None yet
Organizations
1231czx/iter_dpo4_nll_loss_math500_test
Viewer
• Updated • 496 • 5
Viewer
• Updated • 40k • 4
Viewer
• Updated • 40k • 6
Viewer
• Updated • 20k • 6
1231czx/numia_gsm8k_sft_gen2
Viewer
• Updated • 60.1k • 6
1231czx/numia_llama3_math_sft_gen2
Viewer
• Updated • 57.5k • 6
1231czx/numia_llama3_math_sft_gen1
Viewer
• Updated • 15k • 5
1231czx/numia_gsm8k_sft_gen1
Viewer
• Updated • 15k • 6
1231czx/numia_llama3_sft_em_1ep
Viewer
• Updated • 119k • 5
1231czx/fixedbeta05_llama3_sft_math_dpo_type1_7ktype2__7ktype3_ver2_200_more_datatmp10_vllmexp_retest2
Viewer
• Updated • 50k • 6
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2__and_7ktype3_loss100_more_datatmp10_vllmexp_retest2
Viewer
• Updated • 50k • 6
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2__and_7ktype3_loss250_more_datatmp10_vllmexp_retest2
Viewer
• Updated • 50k • 6
1231czx/fixedbeta05_llama3_sft_math_dpo_type1_7ktype2__7ktype3_ver2_250_more_datatmp10_vllmexp_retest2
Viewer
• Updated • 50k • 5
1231czx/fixedbeta05_llama3_sft_math_dpo_type1_7ktype2__7ktype3_ver2_150_more_datatmp10_vllmexp_retest2
Viewer
• Updated • 50k • 5
1231czx/llama3_sft_w2r125k_r2r60k_r60k_ep3_tmp10_vllmexp_retest2
Viewer
• Updated • 5k • 5
1231czx/llama3_sft_w2r125k_r2r60k_r60k_ep3_tmp10_vllmexp_retest
Viewer
• Updated • 5k • 6
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss900_merged_datatmp10
Viewer
• Updated • 20k • 6
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss700_merged_datatmp10
Viewer
• Updated • 20k • 5
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss300_merged_datatmp10
Viewer
• Updated • 20k • 5
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss100_merged_datatmp10
Viewer
• Updated • 20k • 6
1231czx/fixed_beta05_llama3_sft_math_type1_7ktype2_7ktype3_step50
Viewer
• Updated • 20k • 6
1231czx/fixed_beta05_llama3_sft_math_type1_7ktype2_7ktype3_step250
Viewer
• Updated • 50k • 5
1231czx/fixed_beta05_llama3_sft_math_type1_7ktype2_7ktype3_step200
Viewer
• Updated • 50k • 4
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_7ktype3_step250
Viewer
• Updated • 50k • 5
1231czx/fixed_beta05_llama3_sft_math_type1_7ktype2_7ktype3_step150
Viewer
• Updated • 50k • 6
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_7ktype3_step100
Viewer
• Updated • 50k • 5
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss550tmp10_vllmexp
Viewer
• Updated • 5k • 6
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_450tmp10_vllmexp
Viewer
• Updated • 5k • 6
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss500tmp10_vllmexp
Viewer
• Updated • 5k • 5
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_400tmp10_vllmexp
Viewer
• Updated • 5k • 5