metadata
license: apache-2.0
datasets:
- AI-MO/NuminaMath-CoT
- a-m-team/AM-DeepSeek-R1-Distilled-1.4M
base_model:
- jerrimu/ERNIE-21B-REAP
This is a Pre-SFT/DPO checkpoint of IRIS, our ERNIE finetune.
These improvements over ERNIE-21B-REAP have been noted
Benchmark Pre-CPT Post-CPT Δ
ARC-Easy 79.6 83.9 +4.3
ARC-Challenge 50.6 60.4 +9.8
HellaSwag 70.5 78.9 +8.4
Winogrande 67.2 72.1 +4.9