Benjamin Feuer

penfever's activity

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

updated a model 17 minutes ago

open-athena/Snowball-LongLoop-Plumbing-Step3-2026.11.09-r1

Reinforcement Learning • 67B • Updated 17 minutes ago

published a model 17 minutes ago

open-athena/Snowball-LongLoop-Plumbing-Step3-2026.11.09-r1

Reinforcement Learning • 67B • Updated 17 minutes ago

updated a dataset 4 days ago

open-athena/task-trove

Viewer • Updated 4 days ago • 931k • 4.11k • 1

updated 3 models 9 days ago

open-athena/Qwen3-30B-A3B-Chat-Aligned-Base-2026.10.30

Text Generation • 31B • Updated 9 days ago • 740

open-athena/Nemotron-3-Nano-30B-A3B-Chat-Aligned-Base-2026.10.30

Text Generation • 32B • Updated 9 days ago • 680

open-athena/Snowball-67B-A2B-Chat-Aligned-Base-2026.10.22

Text Generation • 67B • Updated 9 days ago • 304

updated 2 datasets 9 days ago

open-athena/Marin-Micro-Eval-210

Viewer • Updated 9 days ago • 660 • 216

open-athena/Marin-Mini-Eval-840

Viewer • Updated 9 days ago • 2.47k • 223

updated a collection 10 days ago

Chat-Aligned Bases

Collection

Pretrained MoE bases after one shared three-stage SFT (chat, thinking, terminal agent), used as comparable starting points for post-training research. • 4 items • Updated 10 days ago

published a model 10 days ago

open-athena/Qwen3.5-35B-A3B-Chat-Aligned-Base-2026.10.31

Text Generation • 35B • Updated 9 days ago • 1.03k

updated a model 10 days ago

open-athena/Qwen3.5-35B-A3B-Chat-Aligned-Base-2026.10.31

Text Generation • 35B • Updated 9 days ago • 1.03k

updated a dataset 10 days ago

open-athena/Marin-Mini-Eval-Policy-Index

Viewer • Updated 9 days ago • 840 • 504

published 3 datasets 10 days ago

open-athena/Marin-Micro-Eval-210

Viewer • Updated 9 days ago • 660 • 216

open-athena/Marin-Mini-Eval-840

Viewer • Updated 9 days ago • 2.47k • 223

open-athena/Marin-Mini-Eval-Policy-Index

Viewer • Updated 9 days ago • 840 • 504

updated a collection 10 days ago

Chat-Aligned Bases

Collection

Pretrained MoE bases after one shared three-stage SFT (chat, thinking, terminal agent), used as comparable starting points for post-training research. • 4 items • Updated 10 days ago

published a model 10 days ago

open-athena/Qwen3-30B-A3B-Chat-Aligned-Base-2026.10.30

Text Generation • 31B • Updated 9 days ago • 740

updated a dataset 10 days ago

open-athena/sft-cold-start-eval-configs-20261030

Viewer • Updated 10 days ago • 1 • 125

published a dataset 10 days ago

open-athena/sft-cold-start-eval-configs-20261030

Viewer • Updated 10 days ago • 1 • 125

published a model 10 days ago

open-athena/Nemotron-3-Nano-30B-A3B-Chat-Aligned-Base-2026.10.30

Text Generation • 32B • Updated 9 days ago • 680