·
AI & ML interests
None yet
Organizations
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_500tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_450tmp10_vllmexp
Viewer
• Updated • 5k • 1
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_400tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_350tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_300tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_250tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_200tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_150tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_100tmp10_vllmexp
Viewer
• Updated • 5k • 3
1231czx/fixed_beta05_llama3_sft_math_type12_8ktype4_and_6ktype3_no_sft_loss700tmp10_vllmexp
Viewer
• Updated • 5k • 1
Viewer
• Updated • 3.95k • 2
1231czx/fixedbeta05_no_sft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_ver2_100tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/nosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_450tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/nosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_250tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_400tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_350tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_300tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_9ktype3_100tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_500tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_450tmp10_vllmexp
Viewer
• Updated • 5k • 1
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_400tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_350tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_300tmp10_vllmexp
Viewer
• Updated • 5k 1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_200tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_150tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/znosft_llama3_sft_math_dpo_type12_8ktype4_7ktype3_ver2_100tmp10_vllmexp
Viewer
• Updated • 5k • 2
1231czx/HanningZhang_Llama3-sft-gsm8k-c2c50K-w2c48K-c100K-2eptmp07_vllmexp
Viewer
• Updated • 3.95k • 2
1231czx/HanningZhang_Llama3-sft-gsm8k-c2c50K-w2c48K-c100K-2eptmp10_vllmexp
Viewer
• Updated • 3.95k • 3
1231czx/HanningZhang_Llama3-sft-gsm8k-c2c50K-w2c48K-c100K-3eptmp07_vllmexp
Viewer
• Updated • 3.95k • 2
1231czx/HanningZhang_Llama3-sft-gsm8k-c2c50K-w2c48K-c100K-3eptmp10_vllmexp
Viewer
• Updated • 3.95k • 2