AI & ML interests
None defined yet.
tmpmodelsave/dpo_llama_type1_gsm8k_8ktype4_150tmp10
Viewer
•
Updated
•
5.28k
•
2
tmpmodelsave/dpollama3_it_gsm8k_5ktype4_150tmp10
Viewer
•
Updated
•
5.28k
•
2
tmpmodelsave/dpo_llama_type1_gsm8k_8ktype4_100tmp10
Viewer
•
Updated
•
5.28k
•
2
tmpmodelsave/dpollama3_it_gsm8k_5ktype4_100tmp10
Viewer
•
Updated
•
5.28k
•
2
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss900_merged_datatmp10
Viewer
•
Updated
•
20k
•
5
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss700_merged_datatmp10
Viewer
•
Updated
•
20k
•
5
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss300_merged_datatmp10
Viewer
•
Updated
•
20k
•
4
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss100_merged_datatmp10
Viewer
•
Updated
•
20k
•
3
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_50_more_datatmp10
Viewer
•
Updated
•
20k
•
4
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss100_more_datatmp10
Viewer
•
Updated
•
50k
•
3
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_150_more_datatmp10
Viewer
•
Updated
•
50k
•
3
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_250_more_datatmp10
Viewer
•
Updated
•
50k
•
5
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_200_more_datatmp10
Viewer
•
Updated
•
50k
•
3
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss250_more_datatmp10
Viewer
•
Updated
•
50k
•
5
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss550tmp10
Viewer
•
Updated
•
5k
•
2
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss500tmp10
Viewer
•
Updated
•
5k
•
5
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_450tmp10
Viewer
•
Updated
•
5k
•
4
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss450tmp10
Viewer
•
Updated
•
5k
•
5
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_400tmp10
Viewer
•
Updated
•
5k
•
3
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss400tmp10
Viewer
•
Updated
•
5k
•
5
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_350tmp10
Viewer
•
Updated
•
5k
•
4
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss350tmp10
Viewer
•
Updated
•
5k
•
4
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_300tmp10
Viewer
•
Updated
•
5k
•
5
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss300tmp10
Viewer
•
Updated
•
5k
•
4
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_250tmp10
Viewer
•
Updated
•
5k
•
3
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss250tmp10
Viewer
•
Updated
•
5k
•
5
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_200tmp10
Viewer
•
Updated
•
5k
•
4
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss200tmp10
Viewer
•
Updated
•
5k
•
5
tmpmodelsave/fixedbeta05_no_sft_llama3_sft_math_dpo_type1_7ktype2_8ktype4_7ktype3_ver2_150tmp10
Viewer
•
Updated
•
5k
•
5
tmpmodelsave/fixed_beta05_llama3_sft_math_type1_3ktype2_8ktype4_and_7ktype3_no_sft_loss150tmp10
Viewer
•
Updated
•
5k
•
5