arxiv:2407.01100
Ziqi wang
wzq016
AI & ML interests
NLP
Organizations
models
41
wzq016/qwen2.5_32B_LR8.0e-7_flt_sky_c8k_m10k_cs_no_cls_sset_4k8k_0502
33B
•
Updated
•
6
wzq016/qwen2.5_32B_LR8.0e-7_filtered_sky_code_8k_math_10k_no_rubric_ablation_4k8k_0501
33B
•
Updated
wzq016/qwen2.5_32B_LR8.0e-7_filtered_sky_code_8k_math_10k_cold_start_same_setting_4k8k_0501
33B
•
Updated
wzq016/qwen2.5_32B_LR5.0e-7_flt_sky_c8k_m10k_rubevi_clsw_4k8k_dstl_ClD_o3_0419_SD
33B
•
Updated
wzq016/qwen2.5_32B_LR1.0e-6_flt_sky_c8k_m10k_rubevi_clsw_4k8k_dstl_Cld_o3_0419_SD_step45
33B
•
Updated
•
6
wzq016/qwen2.5_32B_LR1.0e-6_flt_sky_c8k_m10k_rubevi_clsw_4k8k_dstl_Cld_o3_0419_SD
33B
•
Updated
•
7
wzq016/deepseek_r1_distilled_14B_LR1.0e-6_filtered_sky_code_8k_math_10k_rubric_reasoning_4k512
15B
•
Updated
•
5
wzq016/deepseek_r1_distilled_14B_LR1.0e-6_filtered_sky_code_8k_math_10k_rubric_reasoning_4k128
15B
•
Updated
wzq016/deepseek_r1_distilled_14B_LR1.0e-6_filtered_sky_code_8k_math_10k_rubric_reasoning_4k1k
15B
•
Updated
•
9
wzq016/deepseek_r1_distilled_14B_LR1.0e-6_filtered_sky_code_8k_math_10k_rubric_reasoning_4k2k
15B
•
Updated
•
6
datasets
0
None public yet