An official model example from the paper “PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning”, including weights train
DGME
DGME
AI & ML interests
LLMs
Organizations
None yet
models 8
DGME/pegrl_en2fi_ascend_4B
4B • Updated • 5
DGME/pegrl_en2tr_ascend_4B
4B • Updated • 4
DGME/pegrl_en2tr_4B
4B • Updated • 3
DGME/Qwen2.5-0.5B-Mix
Text Generation • 0.5B • Updated • 2
DGME/Qwen2.5-0.5B-Open-R1-SFT
Text Generation • Updated • 3
DGME/Qwen2.5-0.5B-Open-R1-GRPO
Updated
DGME/Qwen2.5-1.5B-Open-R1-GRPO
Updated
DGME/qwen2.5-3b-mathinstruct
Updated