Adding Evaluation Results
#5
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -86,3 +86,17 @@ A 7b version of the adapter can be found [here](https://huggingface.co/Mikael110
|
|
| 86 |
A 13b version of the adapter can be found [here](https://huggingface.co/Mikael110/llama-2-13b-guanaco-qlora).
|
| 87 |
|
| 88 |
**Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
A 13b version of the adapter can be found [here](https://huggingface.co/Mikael110/llama-2-13b-guanaco-qlora).
|
| 87 |
|
| 88 |
**Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.**
|
| 89 |
+
|
| 90 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 91 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__llama-2-70b-Guanaco-QLoRA-fp16)
|
| 92 |
+
|
| 93 |
+
| Metric | Value |
|
| 94 |
+
|-----------------------|---------------------------|
|
| 95 |
+
| Avg. | 58.32 |
|
| 96 |
+
| ARC (25-shot) | 68.26 |
|
| 97 |
+
| HellaSwag (10-shot) | 88.32 |
|
| 98 |
+
| MMLU (5-shot) | 70.23 |
|
| 99 |
+
| TruthfulQA (0-shot) | 55.69 |
|
| 100 |
+
| Winogrande (5-shot) | 83.98 |
|
| 101 |
+
| GSM8K (5-shot) | 29.8 |
|
| 102 |
+
| DROP (3-shot) | 11.98 |
|