billmianz/rebuttal_SaR_qwen17b_bestN_sft_step400
2B • Updated • 19
Mian Zhang
billmianz
AI & ML interests
None yet
Recent Activity
updated a model 2 days ago
billmianz/rebuttal_SaR_qwen17b_bestN_sft_step400 published a model 2 days ago
billmianz/rebuttal_SaR_qwen17b_bestN_sft_step400 updated a model 2 days ago
billmianz/rebuttal_SaR_qwen17b_bestN_sft_step300Organizations
billmianz/rebuttal_SaR_qwen17b_bestN_sft_step300
2B • Updated • 13
billmianz/rebuttal_SaR_qwen17b_bestN_sft_step200
2B • Updated • 17
billmianz/rebuttal_SaR_qwen17b_bestN_sft_step100
2B • Updated • 14
billmianz/rebuttal_SaR_qwen17b_random_sft_step400
2B • Updated • 16
billmianz/rebuttal_SaR_qwen17b_random_sft_step300
2B • Updated • 10
billmianz/rebuttal_SaR_qwen17b_random_sft_step200
2B • Updated • 12
billmianz/rebuttal_SaR_qwen17b_random_sft_step100
2B • Updated • 18
billmianz/rebuttal_SaR_qwen7b_step400
8B • Updated • 18
billmianz/rebuttal_SaR_qwen7b_step300
8B • Updated • 16
billmianz/rebuttal_SaR_qwen7b_step200
8B • Updated • 12
billmianz/rebuttal_SaR_qwen7b_step100
8B • Updated • 13
billmianz/rebuttal_bestN_sft
2B • Updated • 13
billmianz/rebuttal_random_sft
2B • Updated • 16
billmianz/stage2_gz32_linear_base_pairwise_alpha2_qwen7b_sft_mh_100_step300
8B • Updated • 1
billmianz/stage2_gz32_linear_base_pairwise_alpha2_qwen7b_sft_mh_100_step200
8B • Updated • 1
billmianz/stage2_gz32_baseline_qwen17b_step300
2B • Updated • 2
billmianz/stage2_gz32_baseline_qwen17b_step200
2B • Updated • 2
billmianz/stage2_gz8_linear_base_pairwise_alpha2_qwen7b_sft_mh_100_step300
8B • Updated • 2
billmianz/stage2_gz8_linear_base_pairwise_alpha2_qwen7b_sft_mh_100_step200
8B • Updated
billmianz/stage2_gz8_baseline_qwen17b_step300
2B • Updated • 2
billmianz/stage2_gz8_baseline_qwen17b_step200
2B • Updated • 4
billmianz/stage2_data_ablation_qwen17b_sft_mh_100_step300
2B • Updated • 2
billmianz/stage2_data_ablation_qwen17b_sft_mh_100_step200
2B • Updated • 4
billmianz/qwen17b_nothink_math_step200
2B • Updated • 1
billmianz/qwen17b_nothink_math
Updated
billmianz/stage2_linear_base_qwen7b_sft_mh_100_step400
8B • Updated • 2
billmianz/stage2_linear_base_qwen7b_sft_mh_100_step300
8B • Updated • 1
billmianz/stage2_baseline_qwen7b_sft_mh_100_step400
8B • Updated • 1
billmianz/stage2_baseline_qwen7b_sft_mh_100_step300
8B • Updated • 3