HuggingFaceH4/zephyr-7b-beta

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Methodology3 results

Few-Shot LearningonMedConceptsQA
Accuracy· 2023-10-25
25.058
best: 61.911 (gpt-4-0125-preview)
Zephyr: Direct Distillation of LM Alignment arXiv:2310.16944
Zero-Shot LearningonMedConceptsQA
Accuracy· 2023-10-25
25.538
best: 52.489 (gpt-4-0125-preview)
Zephyr: Direct Distillation of LM Alignment arXiv:2310.16944
Meta-LearningonMedConceptsQA
Accuracy· 2023-10-25
25.058
best: 61.911 (gpt-4-0125-preview)
Zephyr: Direct Distillation of LM Alignment arXiv:2310.16944