27 lines
1.3 KiB
Markdown
27 lines
1.3 KiB
Markdown
|
---
|
||
|
|
license: cc-by-nc-4.0
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
<a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
|
||
|
|
|
||
|
|
# EnsembleV5-Nova-13B
|
||
|
|
|
||
|
|
EnsembleV5-Nova-13B is a merge of [yontaek/llama-2-13B-ensemble-v5](https://huggingface.co/yontaek/llama-2-13B-ensemble-v5) and [Nova-13B-Lora](https://huggingface.co/PulsarAI/Nova-13B-Lora).
|
||
|
|
|
||
|
|
**Note:** I currently can not find the model on hub so the link is broken.
|
||
|
|
|
||
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PulsarAI__EnsembleV5-Nova-13B)
|
||
|
|
|
||
|
|
| Metric | Value |
|
||
|
|
|-----------------------|---------------------------|
|
||
|
|
| Avg. | 49.65 |
|
||
|
|
| ARC (25-shot) | 62.71 |
|
||
|
|
| HellaSwag (10-shot) | 82.55 |
|
||
|
|
| MMLU (5-shot) | 56.79 |
|
||
|
|
| TruthfulQA (0-shot) | 49.86 |
|
||
|
|
| Winogrande (5-shot) | 76.24 |
|
||
|
|
| GSM8K (5-shot) | 10.77 |
|
||
|
|
| DROP (3-shot) | 8.64 |
|