LLucass/Tanh_PRESS_GRPO_1.0_beta_0.01_n_generations_12
2B
•
Updated
•
5
Cheng Wang
LLucass
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 days ago
Model-Task Alignment Drives Distinct RL Outcomes
commented on
a paper
2 days ago
Model-Task Alignment Drives Distinct RL Outcomes
updated
a model
about 2 months ago
LLucass/GRPO-7B
Organizations
LLucass/Tanh_PRESS_GRPO_4.0_beta_0.01_n_generations_12
2B
•
Updated
•
5
LLucass/Tanh_PRESS_GRPO_0.5_beta_0.01_n_generations_12
2B
•
Updated
•
5
LLucass/PRESS_GRPO_2.0_beta_0.01_n_generation_12
2B
•
Updated
•
5
LLucass/GRPO_beta_0.01_n_generation_12
2B
•
Updated
•
5
LLucass/Tanh_PRESS_GRPO_2.0_beta_0.04
2B
•
Updated
•
5
LLucass/Tanh_PRESS_GRPO_1.0_beta_0.04
2B
•
Updated
•
5
LLucass/Tanh_PRESS_GRPO_2.0_beta_0.01
2B
•
Updated
•
4
LLucass/ACC_GRPO_beta_0.01
2B
•
Updated
•
5
LLucass/ACC_PRESS_GRPO_2.0_beta_0.01
2B
•
Updated
•
5
LLucass/PRESS_GRPO_4.0_beta_0.01
2B
•
Updated
•
5
LLucass/PRESS_GRPO_2.0_beta_0.01
2B
•
Updated
•
5
LLucass/GRPO_beta_0.01
2B
•
Updated
•
5
LLucass/PRESS_GRPO_2.0_beta_0.001
2B
•
Updated
•
5
LLucass/PRESS_GRPO_1.0_beta_0.001
2B
•
Updated
•
5
LLucass/GRPO_beta
Updated
LLucass/PRESS_GRPO_0.5_beta_0.001
2B
•
Updated
•
5
LLucass/GRPO_beta_0.001
2B
•
Updated
•
5
LLucass/PRESS_GRPO_0.2
2B
•
Updated
•
5
LLucass/PRESS_GRPO_4.0
Updated
LLucass/PRESS_GRPO_2.0
2B
•
Updated
•
5
LLucass/PRESS_GRPO_1.5
Updated
LLucass/PRESS_GRPO_1.0
2B
•
Updated
•
4
LLucass/PRESS_GRPO_0.5
2B
•
Updated
•
5
LLucass/DR_GRPO
Updated
LLucass/qwen-math-7b-entropy-top1k
Updated
LLucass/Entropy-Maximization-All-Step2
8B
•
Updated
•
6
LLucass/Entropy-Minimization-All-Step2
8B
•
Updated
•
5
LLucass/Entropy-Maximization-Bot20-Step2
8B
•
Updated
•
6
LLucass/FF_L0.2_H0.2_grpo
Text Generation
•
2B
•
Updated
•
7