OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
Open paper
Benchmark
Model
Rank
Results
code-generation-on-mbpp
OptiMer
#50
Accuracy: 72.6
sentence-completion-on-hellaswag
OptiMer (Gemma 3 27B)
#54
Accuracy: 82.98
Rank counts only results with a code link.