Mariia Trofimova

vim-ary's activity

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

New activity in nebius/SWE-rebench-openhands-Qwen3-30B-A3B 1 day ago

Exactly what I have been looking for.

❤️ 1

1

#1 opened 3 days ago by

leonletto

liked 2 models 3 days ago

nebius/SWE-rebench-openhands-Qwen3-235B-A22B

Text Generation • 235B • Updated 3 days ago • 8 • 3

nebius/SWE-rebench-openhands-Qwen3-30B-A3B

Text Generation • 31B • Updated 3 days ago • 45 • 7

updated 2 models 21 days ago

nebius/SWE-rebench-openhands-Qwen3-30B-A3B

Text Generation • 31B • Updated 3 days ago • 45 • 7

nebius/SWE-rebench-openhands-Qwen3-235B-A22B

Text Generation • 235B • Updated 3 days ago • 8 • 3

updated a dataset 22 days ago

nebius/SWE-rebench-openhands-trajectories

Viewer • Updated 3 days ago • 67.1k • 144 • 21

updated a collection 25 days ago

Openhands Trajectories

Collection

Dataset of 67,074 OpenHands trajectories collected with Qwen3-Coder-480B-A35B-Instruct and two RFT checkpoints trained on the data • 3 items • Updated 3 days ago • 6

New activity in Qwen/Qwen3-Coder-30B-A3B-Instruct 2 months ago

SWE-bench Verified Repro

➕ 1

#30 opened 2 months ago by

vim-ary

upvoted a paper 5 months ago

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

Paper • 2508.03501 • Published Aug 5 • 59

commented 2 papers 5 months ago

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

Paper • 2508.03501 • Published Aug 5 • 59 •

4

Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning

Paper • 2508.03501 • Published Aug 5 • 59 •

4

liked 2 datasets about 1 year ago

nebius/SWE-agent-trajectories

Viewer • Updated Dec 23, 2024 • 80k • 1.23k • 67

nebius/SWE-bench-extra

Viewer • Updated May 28 • 6.38k • 283 • 46