Daniil Larionov

Rexhaif's activity

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

liked a Space 2 days ago

Running

26

Weight-Space Geometry of Offline Reasoning Training

🧭

26

Interactive weight-space geometry of six reasoning losses

updated 7 models about 2 months ago

Rexhaif/anon-14B-SFT-Reasoning

15B • Updated May 4 • 9

Rexhaif/anon-8B-SFT-Reasoning

8B • Updated May 4 • 8

Rexhaif/anon-4B-SFT-Reasoning

4B • Updated May 4 • 6

Rexhaif/anon-0.6B-SFT-Reasoning

0.6B • Updated May 4 • 7

Rexhaif/anon-4b-rl-thinking

4B • Updated Apr 26 • 12 • 1

Rexhaif/anon-0.6B-RL-Thinking

0.6B • Updated Apr 26 • 11

Rexhaif/anon-8B-RL-Thinking

8B • Updated Apr 25 • 5

updated 2 models 2 months ago

Rexhaif/anon-14B-RL-Thinking

15B • Updated Apr 18 • 6

Rexhaif/Qwen3-14B-Tulu-SFT-Dolci-Reasoning-100k

15B • Updated Apr 15 • 4

published a model 2 months ago

Rexhaif/Qwen3-14B-Tulu-SFT-Dolci-Reasoning-100k

15B • Updated Apr 15 • 4

updated a model 2 months ago

Rexhaif/Qwen3-8B-Tulu-SFT-Dolci-Reasoning-100k

8B • Updated Apr 15 • 3

published a model 2 months ago

Rexhaif/Qwen3-8B-Tulu-SFT-Dolci-Reasoning-100k

8B • Updated Apr 15 • 3

updated 2 models 2 months ago

Rexhaif/Qwen3-4B-Tulu-SFT-Dolci-Reasoning-100k

4B • Updated Apr 15 • 4 • 1

Rexhaif/Qwen3-0.6B-Tulu-SFT-Dolci-Reasoning-100k

0.6B • Updated Apr 15 • 4

published 2 models 2 months ago

Rexhaif/Qwen3-4B-Tulu-SFT-Dolci-Reasoning-100k

4B • Updated Apr 15 • 4 • 1

Rexhaif/Qwen3-0.6B-Tulu-SFT-Dolci-Reasoning-100k

0.6B • Updated Apr 15 • 4

updated a model 3 months ago

Rexhaif/anon-8B-RL

8B • Updated Apr 7 • 7

published a model 3 months ago

Rexhaif/anon-14B-RL-Thinking

15B • Updated Apr 18 • 6

liked a dataset 3 months ago

ServiceNow-AI/eva

Viewer • Updated Mar 24 • 50 • 69 • 71