Generate reward scores using generative models.
rubricreward
non-profit
AI & ML interests
Robust Reward Model is all you need
Recent Activity
View all activity
Collections
3
models
29
rubricreward/R3-Phi-4-reasoning-plus-14k
Updated
•
23
•
1
rubricreward/R3-Phi-4-reasoning-plus-4k
Text Generation
•
Updated
•
12
rubricreward/R3-Phi-4-reasoning-plus-LoRA-4k
Text Generation
•
Updated
•
53
rubricreward/R3-Qwen3-4B-14k
Text Generation
•
Updated
•
15
•
1
rubricreward/R3-Qwen3-4B-4k
Text Generation
•
Updated
•
9
rubricreward/R3-Qwen3-4B-LoRA-4k
Text Generation
•
Updated
•
5
rubricreward/R3-Qwen3-8B-14k
Text Generation
•
Updated
•
42
•
1
rubricreward/R3-Qwen3-8B-4k
Text Generation
•
Updated
•
5
rubricreward/R3-Qwen3-8B-LoRA-4k
Text Generation
•
Updated
•
6
rubricreward/R3-Qwen3-14B-14k
Text Generation
•
Updated
•
19
•
1
datasets
46
rubricreward/R3-Dataset-20K
Viewer
•
Updated
•
20k
•
27
•
1
rubricreward/R3-Dataset-14K
Viewer
•
Updated
•
13.8k
•
31
rubricreward/R3-Dataset-4K
Viewer
•
Updated
•
3.95k
•
31
rubricreward/R3-eval-XSUM
Viewer
•
Updated
•
5.36k
•
27
rubricreward/R3-eval-RM-Bench
Viewer
•
Updated
•
11.9k
•
11
rubricreward/R3-eval-BBH
Viewer
•
Updated
•
13.5k
•
12
rubricreward/R3-eval-MMLU-STEM
Viewer
•
Updated
•
6.31k
•
15
rubricreward/R3-eval-reward-bench
Viewer
•
Updated
•
2.99k
•
8
rubricreward/llm-metric-MMLU-Pro
Viewer
•
Updated
•
24.2k
•
29
rubricreward/R3-eval-FeedbackBench
Viewer
•
Updated
•
1k
•
14