LLaMA 2 13B (0-shot)

Reported on 3 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing3 results

Question AnsweringonPIQA
Accuracy· 2023-07-18
80.5
best: 90.1 (Unicorn 11B (fine-tuned))
Llama 2: Open Foundation and Fine-Tuned Chat Models arXiv:2307.09288
Question AnsweringonBoolQ
Accuracy· 2023-07-18
81.7
best: 99.87 (Mistral-Nemo 12B (HPT))
Llama 2: Open Foundation and Fine-Tuned Chat Models arXiv:2307.09288
Sentence CompletiononHellaSwag
Accuracy· 2023-07-18
80.7
best: 96.1 (CompassMTL 567M with Tailor)
Llama 2: Open Foundation and Fine-Tuned Chat Models arXiv:2307.09288