andre930/single_head_soc_1536
Updated
Andre X
andre930
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Simultaneous Multi-objective Alignment Across Verifiable and
Non-verifiable Rewards updated a model about 1 month ago
andre930/rl-controller-pp-step49 published a model about 1 month ago
andre930/rl-controller-pp-step49Organizations
None yet
andre930/single_head_soc_1728
Updated
andre930/single_head_soc
Updated
andre930/my_unified_model_classification_v_only
8B • Updated • 2
andre930/my_unified_model_classification_all_2108
8B • Updated • 2
andre930/my_unified_model_classification_all_1890
8B • Updated • 2
andre930/my_unified_model_classification_all_1260
8B • Updated • 1
andre930/single_dpo_math_good_sft_5e7_2ep_just_acc_LATEST
Updated
andre930/sm_single_head_dpo_qwen25_fsdp_5e6_2ep_bz128_LATEST_with_SFT_updated
Updated
andre930/eng_prm
8B • Updated • 1
andre930/unified_dpo_5e_6_2ep_single_head
Updated
andre930/acc_latest_filtered
8B • Updated • 2