·
AI & ML interests
None yet
Organizations
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss450tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_350tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss400tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_300tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss350tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_250tmp10_vllmexp
Viewer
• Updated • 5k • 1
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss300tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_200tmp10_vllmexp
Viewer
• Updated • 5k • 1
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss250tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_150tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss150tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_100tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss100tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss200tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_no_sft_type3_7k_step150_more_datatmp10_vllmexp1
Viewer
• Updated • 50k • 2
1231czx/fixed_no_sft_type3_7k_step150_more_datatmp10_vllmexp
Viewer
• Updated • 50k • 2
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss650tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss600tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss550tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss500tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss450tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss400tmp10_vllmexp
Viewer
• Updated • 5k • 1
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss350tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss300tmp10_vllmexp
Viewer
• Updated • 5k • 1
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss250tmp10_vllmexp
Viewer
• Updated • 5k • 1
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss150tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss100tmp10_vllmexp
Viewer
• Updated • 5k • 5
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_650tmp10_vllmexp
Viewer
• Updated • 5k • 3
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_600tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_550tmp10_vllmexp
Viewer
• Updated • 5k • 2