lzc0525

lzc0525 's models 124

Sort:  Recently updated

lzc0525/qwen_math_7b_dpo_ourdata_11

Updated Jun 27

lzc0525/qwen_math_7b_dpo_ourdata_10

Updated Jun 27

lzc0525/outputs_ipo_phi

Updated Jun 26

lzc0525/outputs_ipo

Updated Jun 26

lzc0525/qwen_reason_7b_dpo_ultra_6

Updated Jun 26

lzc0525/qwen_reason_7b_dpo_ultra_5

Updated Jun 26

lzc0525/outputs_ipo_qwen

Updated Jun 26

lzc0525/outputs_kto

Updated Jun 26

lzc0525/qwen_reason_7b_dpo_ultra_4

Updated Jun 26

lzc0525/qwen_reason_7b_dpo_ultra_3

Updated Jun 26

lzc0525/qwen_reason_7b_dpo_ultra_2

Updated Jun 26

lzc0525/qwen_reason_7b_dpo_ultra_1

Updated Jun 26

lzc0525/qwen_reason_7b_dpo_ultra_0

Updated Jun 26

lzc0525/qwen_math_7b_dpo_ourdata_9

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_8

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_7

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_6

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_5

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_4

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_3

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_2

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_1

Updated Jun 25

lzc0525/qwen_math_7b_dpo_ourdata_0

Updated Jun 25

lzc0525/qwen-math

Updated Apr 28

lzc0525/math_llama3_reset_dpo_100_0_pro1.0

4B • Updated Mar 17

lzc0525/math_llama3_reset_dpo_100_0_pro0.83

4B • Updated Mar 17

lzc0525/math_llama3_reset_dpo_100_0_pro0.67

4B • Updated Mar 17

lzc0525/math_llama3_reset_dpo_100_0_pro0.5

4B • Updated Mar 17 • 1

lzc0525/math_llama3_reset_dpo_100_0_pro0.33

4B • Updated Mar 17

lzc0525/math_llama3_reset_dpo_100_0_pro0.17

4B • Updated Mar 17