Self-Hinting Language Models Enhance Reinforcement Learning
Baohao Liao
baohao
AI & ML interests
NLP
Recent Activity
updated
a model
1 day ago
baohao/SAGE-light_Qwen3-4B-Instruct-2507
updated
a model
1 day ago
baohao/SAGE-light_Llama-3.2-3B-Instruct
updated
a model
1 day ago
baohao/SAGE-light_Qwen2.5-7B-Instruct
Organizations
models
15
baohao/SAGE-light_Qwen3-4B-Instruct-2507
4B
•
Updated
•
12
baohao/SAGE-light_Llama-3.2-3B-Instruct
4B
•
Updated
•
11
baohao/SAGE-light_Qwen2.5-7B-Instruct
8B
•
Updated
•
16
baohao/SAGE_Qwen3-4B-Instruct-2507
4B
•
Updated
•
9
baohao/SAGE_Qwen2.5-7B-Instruct
8B
•
Updated
•
15
baohao/SAGE_Llama-3.2-3B-Instruct
4B
•
Updated
•
17
baohao/tdms
Updated
baohao/deberta-v3-base-2bit-32rank-0.1dropout
Text Classification
•
Updated
baohao/Llama-2-7b-hf-3bit-64rank-0.1dropout-c4
Text Generation
•
Updated
baohao/Llama-2-7b-hf-4bit-64rank-0.1dropout
Text Generation
•
Updated
datasets
24
baohao/scaf-grpo_train
Viewer
•
Updated
•
15k
•
8
baohao/luffy_train
Viewer
•
Updated
•
15k
•
9
baohao/sage_train
Viewer
•
Updated
•
15k
•
13
baohao/sage_validation
Viewer
•
Updated
•
1.67k
•
8
baohao/olympiadbench
Viewer
•
Updated
•
675
•
8
baohao/mmlu_pro
Viewer
•
Updated
•
12k
•
24
baohao/minerva_math
Viewer
•
Updated
•
272
•
8
baohao/math500
Viewer
•
Updated
•
500
•
6
baohao/gpqa
Viewer
•
Updated
•
198
•
8
baohao/amc23
Viewer
•
Updated
•
40
•
8