R3 Models - a rubricreward Collection

rubricreward 's Collections

R3 Benchmark Datasets

R3 Models

updated Jun 5

Generate reward scores using generative models.

rubricreward/R3-Qwen3-14B-LoRA-4k

Text Generation • 15B • Updated May 21 • 113 • 2
rubricreward/R3-Qwen3-14B-4k

Text Generation • 15B • Updated May 21 • 20 • 4
rubricreward/R3-Qwen3-14B-14k

Text Generation • 15B • Updated May 21 • 21 • 2
rubricreward/R3-Qwen3-8B-LoRA-4k

Text Generation • 8B • Updated May 21 • 11 • 1
rubricreward/R3-Qwen3-8B-4k

Text Generation • 8B • Updated May 21 • 10 • 1
rubricreward/R3-Qwen3-8B-14k

Text Generation • 8B • Updated May 21 • 15 • 1
rubricreward/R3-Qwen3-4B-LoRA-4k

Text Generation • 4B • Updated May 21 • 10 • 1
rubricreward/R3-Qwen3-4B-4k

Text Generation • 4B • Updated May 21 • 15 • 1
rubricreward/R3-Qwen3-4B-14k

Text Generation • 4B • Updated May 21 • 14 • 1
rubricreward/R3-Phi-4-reasoning-plus-LoRA-4k

Text Generation • 15B • Updated May 21 • 4 • 1
rubricreward/R3-Phi-4-reasoning-plus-4k

Text Generation • 15B • Updated May 21 • 99 • 1
rubricreward/R3-Phi-4-reasoning-plus-14k

Text Generation • 15B • Updated May 26 • 5 • 2