DGME

DGME's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 2 models 4 days ago

DGME/pegrl_en2fi_ascend_4B

4B • Updated 4 days ago • 13

DGME/pegrl_en2tr_ascend_4B

4B • Updated 4 days ago • 13

updated a collection 4 days ago

PEGRL

Collection

An official model example from the paper “PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning”, including weights train • 4 items • Updated 4 days ago

published 2 models 4 days ago

DGME/pegrl_en2tr_ascend_4B

4B • Updated 4 days ago • 13

DGME/pegrl_en2fi_ascend_4B

4B • Updated 4 days ago • 13

updated a collection 4 days ago

PEGRL

Collection

An official model example from the paper “PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning”, including weights train • 4 items • Updated 4 days ago

updated a model 4 days ago

DGME/pegrl_en2tr_4B

4B • Updated 4 days ago • 9

published a model 4 days ago

DGME/pegrl_en2tr_4B

4B • Updated 4 days ago • 9

upvoted a paper 2 months ago

PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning

Paper • 2602.03352 • Published Feb 3 • 1

updated a dataset 3 months ago

DGME/FLORES-200

Viewer • Updated Jan 13 • 185k • 123

published a dataset 3 months ago

DGME/FLORES-200

Viewer • Updated Jan 13 • 185k • 123

updated a dataset 5 months ago

DGME/wmt25

Viewer • Updated Nov 20, 2025 • 102k • 58

published a dataset 5 months ago

DGME/wmt25

Viewer • Updated Nov 20, 2025 • 102k • 58

updated a model 6 months ago

DGME/Qwen2.5-0.5B-Mix

Text Generation • 0.5B • Updated Nov 3, 2025 • 2

published a model 6 months ago

DGME/Qwen2.5-0.5B-Mix

Text Generation • 0.5B • Updated Nov 3, 2025 • 2

New activity in ByteDance-Seed/Seed-X-PPO-7B 6 months ago

looks it not works well with vllm 0.10.1.1

👍 1

6

#20 opened 8 months ago by

Yongzheng

upvoted a paper 6 months ago

Making Mathematical Reasoning Adaptive

Paper • 2510.04617 • Published Oct 6, 2025 • 23

upvoted a paper 7 months ago

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

Paper • 2508.14460 • Published Aug 20, 2025 • 85