·
AI & ML interests
Machine learning, RLHF
Organizations
weqweasdas/qwen7b_grpo_ver2_step80_with_score_passn
Viewer
• Updated • 1k • 2
weqweasdas/qwmathbase_raftpp_bz128_step90_with_score_passn
Viewer
• Updated • 1k • 4
weqweasdas/qwmathbase_raftpp_bz128_step60_with_score_passn
Viewer
• Updated • 1k • 5
weqweasdas/qwmathbase_raftpp_bz128_step20_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwen15b_raftpp_n4_step30_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwen15b_raftpp_n4_step60_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwen15b_raftpp_n4_step90_with_score_passn
Viewer
• Updated • 1k • 4
weqweasdas/qwen7b_raftpp_step100_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwen7b_raftpp_step60_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwen7b_raftpp_step20_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwen7b_step90_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwen7b_step30_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwen7b_step60_with_score_passn
Viewer
• Updated • 1k • 5
weqweasdas/qwen15b_step60_with_score_passn
Viewer
• Updated • 1k • 3
weqweasdas/qwn_reinforce_rej340_minerva_math
Viewer
• Updated • 272 • 7
weqweasdas/qwn_reinforce_rej340_math
Viewer
• Updated • 500 • 3
weqweasdas/qwn_reinforce_rej320_olympiadbench
Viewer
• Updated • 675 • 4
weqweasdas/qwn_reinforce_rej320_minverva_math
Viewer
• Updated • 272 • 3
weqweasdas/qwn_reinforce_rej320_math
Viewer
• Updated • 500 • 3
weqweasdas/llama_grpo_new_test_olympiadbench
Viewer
• Updated • 675 • 5
weqweasdas/llama_grpo_new_test_minerva_math
Viewer
• Updated • 272 • 5
weqweasdas/llama_grpo_new_test_math
Viewer
• Updated • 500 • 3
weqweasdas/qw_grpo_new_test_olyn
Viewer
• Updated • 675 • 3
weqweasdas/qw_grpo_new_test_minerva_math
Viewer
• Updated • 675 • 5
weqweasdas/qw_grpo_new_test_math
Viewer
• Updated • 500 • 3
Viewer
• Updated • 675 • 3
weqweasdas/qw_rej_minerval
Viewer
• Updated • 272 • 3
Viewer
• Updated • 500 • 3
weqweasdas/llama_rej_minder_val
Viewer
• Updated • 272 • 3
Viewer
• Updated • 500 • 3