Self-Hinting Language Models Enhance Reinforcement Learning
Baohao Liao
baohao
AI & ML interests
NLP
Recent Activity
updated
a model about 3 hours ago
baohao/byt5-base-optim_clean-final_fold0_ep20bs1x8lr1e-4_avg5 published
a model about 3 hours ago
baohao/byt5-base-optim_clean-final_fold0_ep20bs1x8lr1e-4_avg5 updated
a model about 20 hours ago
baohao/byt5-base-optim_clean_fold0_ep10bs2x16lr1e-4_best Organizations
models 19
baohao/byt5-base-optim_clean-final_fold0_ep20bs1x8lr1e-4_avg5
0.6B • Updated
baohao/byt5-base-optim_clean_fold0_ep10bs2x16lr1e-4_best
0.6B • Updated
baohao/byt5-base-optim_final_fold0_ep20bs32lr2e-4_best
0.6B • Updated
• 13
baohao/byt5-akkadian-optimized-34x
0.6B • Updated
• 14
baohao/SAGE-light_Qwen3-4B-Instruct-2507
4B • Updated
• 19
baohao/SAGE-light_Llama-3.2-3B-Instruct
4B • Updated
• 22
baohao/SAGE-light_Qwen2.5-7B-Instruct
8B • Updated
• 28 • 2
baohao/SAGE_Qwen3-4B-Instruct-2507
4B • Updated
• 13
baohao/SAGE_Qwen2.5-7B-Instruct
8B • Updated
• 20
baohao/SAGE_Llama-3.2-3B-Instruct
4B • Updated
• 25
datasets 24
baohao/sage_validation
Viewer
• Updated
• 1.67k • 16
baohao/luffy_train
Viewer
• Updated
• 15k • 15
baohao/sage_train
Viewer
• Updated
• 15k • 29
baohao/scaf-grpo_train
Viewer
• Updated
• 15k • 16
baohao/olympiadbench
Viewer
• Updated
• 675 • 198
baohao/mmlu_pro
Viewer
• Updated
• 12k • 55
baohao/minerva_math
Viewer
• Updated
• 272 • 122
baohao/math500
Viewer
• Updated
• 500 • 129
baohao/gpqa
Viewer
• Updated
• 198 • 148
baohao/amc23
Viewer
• Updated
• 40 • 130