·
AI & ML interests
None yet
Organizations
lzc0525/math_llama3_reset_dpo_100_0_pro0.0
4B • Updated • 1
lzc0525/math_llama3_reset_dpo_100_0_1.0
4B • Updated • 1
lzc0525/math_llama3_reset_dpo_100_0_0.83
4B • Updated • 1
lzc0525/math_llama3_reset_dpo_100_0_0.67
4B • Updated • 1
lzc0525/math_llama3_reset_dpo_100_0_0.5
4B • Updated • 1
lzc0525/math_llama3_reset_dpo_100_0_0.33
4B • Updated lzc0525/math_llama3_reset_dpo_100_0_0.17
4B • Updated • 1
lzc0525/math_llama3_reset_dpo_100_0_0.0
4B • Updated • 1
lzc0525/math_phi3_simpo_100_0
4B • Updated • 1
lzc0525/math_phi3_simpo_80_0
4B • Updated • 1
lzc0525/math_phi3_dpo_100_0
4B • Updated lzc0525/math_phi3_simpo_60_0
4B • Updated • 1
lzc0525/math_phi3_dpo_80_0
4B • Updated • 1
lzc0525/math_phi3_simpo_40_0
4B • Updated • 1
lzc0525/math_phi3_dpo_60_0
4B • Updated • 1
lzc0525/math_phi3_dpo_40_0
4B • Updated • 1
lzc0525/math_phi3_simpo_20_0
4B • Updated • 1
lzc0525/math_phi3_dpo_20_0
4B • Updated • 1
lzc0525/math_phi3_simpo_0_0
4B • Updated • 1
lzc0525/math_phi3_dpo_0_0
4B • Updated • 1
lzc0525/math_phi3_dpo_100_100
4B • Updated • 1
lzc0525/math_phi3_dpo_100_80
4B • Updated • 1
lzc0525/math_phi3_dpo_100_60
4B • Updated • 1
lzc0525/math_phi3_dpo_100_40
4B • Updated • 1
lzc0525/math_phi3_dpo_100_20
4B • Updated • 1
lzc0525/math_llama3_simpo_100_0
4B • Updated • 1
lzc0525/math_llama3_simpo_80_0
4B • Updated • 1
lzc0525/math_llama3_simpo_20_0
4B • Updated • 1
lzc0525/math_llama3_simpo_60_0
4B • Updated • 1
lzc0525/math_llama3_simpo_0_0
4B • Updated • 1