AmberYifan/qwen3-4b_openrubrics_v2_grpo_structure_only_step60
4B • Updated • 8
Yifan Wang
AmberYifan
AI & ML interests
None yet
Recent Activity
updated a model 1 day ago
AmberYifan/capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_random_b8000_s0 published a model 1 day ago
AmberYifan/capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_random_b8000_s0 updated a model 1 day ago
AmberYifan/capsd-qwen3-sciweb-stackexchange-Qwen3-4B-Base-science_ppl_b8000_s0Organizations
AmberYifan/qwen3-4b_openrubrics_v2_grpo_reward_model_step60
4B • Updated • 2
AmberYifan/qwen3-4b_openrubrics_v2_grpo_reward_model-Qwen3-1.7B_step60
4B • Updated • 1
AmberYifan/qwen3-4b_openrubrics_v2_grpo_reward_model-FsfairX-LLaMA3-RM-v0.1_step60
4B • Updated • 2
AmberYifan/qwen3-4b_openrubric_empo_embed_step60
4B • Updated • 8
AmberYifan/qwen3-4b_aime_ttrl_step45
4B • Updated • 3
AmberYifan/qwen3-4b_aime_ttrl-new_step45
4B • Updated • 4
AmberYifan/qwen3-4b_aime_ppo_structure_only_step45
4B • Updated • 3
AmberYifan/qwen3-4b_aime_ppo_acc_only_step45
4B • Updated • 3
AmberYifan/qwen3-4b_aime_grpo_structure_only_step45
4B • Updated • 2
AmberYifan/qwen3-4b_aime_grpo_structure_only_new_step_split_step45
4B • Updated • 6
AmberYifan/qwen3-4b_aime_grpo_structure_only_new_step_split_kmeans_step45
4B • Updated • 2
AmberYifan/qwen3-4b_aime_grpo_structure_Local_only_new_step_split_kmeans_step45
4B • Updated • 3
AmberYifan/qwen3-4b_aime_grpo_structure_Global_only_new_step_split_kmeans_step45
4B • Updated • 2
AmberYifan/qwen3-4b_aime_grpo_sarl_step45
4B • Updated • 9
AmberYifan/qwen3-4b_aime_grpo_acc_structure_step45
4B • Updated • 9
AmberYifan/qwen3-4b_aime_grpo_acc_only_step45
4B • Updated • 4
AmberYifan/qwen3-4b_aime_format-length_step45
4B • Updated • 3
AmberYifan/qwen3-4b_aime_empo_step45
4B • Updated • 4
AmberYifan/qwen3-4b_aime_empo-new_step45
4B • Updated • 3
AmberYifan/qwen3-4b-base_aime_grpo_structure_only_step45
4B • Updated • 3
AmberYifan/qwen3-4b-base_aime_grpo_acc_structure_step45
4B • Updated • 3
AmberYifan/qwen3-4b-base_aime_grpo_acc_only_step45
4B • Updated • 2
AmberYifan/qwen2.5-7b_ultrafeedback_grpo_structure_only_step38
8B • Updated • 2
AmberYifan/qwen2.5-7b_openrubrics_v2_grpo_structure_only_step60
8B • Updated • 3
AmberYifan/qwen2.5-7b_openrubrics_v2_grpo_structure_only_lr5e-7_kl0.01_clip0.3_step60
8B • Updated • 2
AmberYifan/qwen2.5-7b_openrubrics_v2_grpo_structure_only_lr5e-7_kl0.005_step60
8B • Updated • 3
AmberYifan/qwen2.5-7b_openrubrics_v2_grpo_structure_only_kmeans_lr5e-7_kl0.01_clip0.3_step60
8B • Updated • 3
AmberYifan/qwen2.5-7b_aime_grpo_structure_only_step45
8B • Updated • 4
AmberYifan/qwen2.5-7b_aime_grpo_acc_structure_step45
8B • Updated • 2