LLaMA-3 8B+MoSLoRA

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

Question AnsweringonOpenBookQA
Accuracy· 2024-06-16
86.8
best: 95.9 (GPT-4 + knowledge base)
Mixture-of-Subspaces in Low-Rank Adaptation arXiv:2406.11909