regulusv's picture

regulusv

regulus4869

·

AI & ML interests

None yet

Organizations

models 4

regulus4869/ppo-qwen-gsm8k

Updated Mar 17, 2025

regulus4869/ppo_trained_model_gsm8k_ppo_500examples

Text Generation • 0.5B • Updated Mar 17, 2025 • 1

regulus4869/Qwen2.5-1.5b-grpo

Text Generation • 2B • Updated Mar 17, 2025 • 1

regulus4869/grpo_trained_model

Text Generation • 3B • Updated Feb 27, 2025 • 1

datasets 0

None public yet