metadata
tags:
- llama
- vicuna
- text-generation-inference
NOTE: Get the new version here: https://huggingface.co/eachadea/vicuna-13b-1.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 45.7 |
| ARC (25-shot) | 51.71 |
| HellaSwag (10-shot) | 79.94 |
| MMLU (5-shot) | 50.84 |
| TruthfulQA (0-shot) | 52.68 |
| Winogrande (5-shot) | 71.03 |
| GSM8K (5-shot) | 7.58 |
| DROP (3-shot) | 6.1 |