·
AI & ML interests
None yet
Organizations
lzc0525/qwen_math_7b_dpo_ourdata_11
Updated
lzc0525/qwen_math_7b_dpo_ourdata_10
Updated
lzc0525/qwen_reason_7b_dpo_ultra_6
Updated
lzc0525/qwen_reason_7b_dpo_ultra_5
Updated
lzc0525/qwen_reason_7b_dpo_ultra_4
Updated
lzc0525/qwen_reason_7b_dpo_ultra_3
Updated
lzc0525/qwen_reason_7b_dpo_ultra_2
Updated
lzc0525/qwen_reason_7b_dpo_ultra_1
Updated
lzc0525/qwen_reason_7b_dpo_ultra_0
Updated
lzc0525/qwen_math_7b_dpo_ourdata_9
Updated
lzc0525/qwen_math_7b_dpo_ourdata_8
Updated
lzc0525/qwen_math_7b_dpo_ourdata_7
Updated
lzc0525/qwen_math_7b_dpo_ourdata_6
Updated
lzc0525/qwen_math_7b_dpo_ourdata_5
Updated
lzc0525/qwen_math_7b_dpo_ourdata_4
Updated
lzc0525/qwen_math_7b_dpo_ourdata_3
Updated
lzc0525/qwen_math_7b_dpo_ourdata_2
Updated
lzc0525/qwen_math_7b_dpo_ourdata_1
Updated
lzc0525/qwen_math_7b_dpo_ourdata_0
Updated
lzc0525/math_llama3_reset_dpo_100_0_pro1.0
4B
•
Updated
•
1
lzc0525/math_llama3_reset_dpo_100_0_pro0.83
4B
•
Updated
•
1
lzc0525/math_llama3_reset_dpo_100_0_pro0.67
4B
•
Updated
•
1
lzc0525/math_llama3_reset_dpo_100_0_pro0.5
4B
•
Updated
•
1
lzc0525/math_llama3_reset_dpo_100_0_pro0.33
4B
•
Updated
•
1
lzc0525/math_llama3_reset_dpo_100_0_pro0.17
4B
•
Updated
•
1