Adding Evaluation Results
Browse files
README.md
CHANGED
|
@@ -32,4 +32,16 @@ Quantizationed versions of this model is available thanks to [TheBloke](https://
|
|
| 32 |
|
| 33 |
##### AWQ
|
| 34 |
|
| 35 |
-
- [TheBloke/Dolphin2.1-OpenOrca-7B-AWQ](https://huggingface.co/TheBloke/Dolphin2.1-OpenOrca-7B-AWQ)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
|
| 33 |
##### AWQ
|
| 34 |
|
| 35 |
+
- [TheBloke/Dolphin2.1-OpenOrca-7B-AWQ](https://huggingface.co/TheBloke/Dolphin2.1-OpenOrca-7B-AWQ)
|
| 36 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) [(📑 Detailed Results)](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Dolphin2.1-OpenOrca-7B)
|
| 37 |
+
|
| 38 |
+
| Metric | Value |
|
| 39 |
+
|-----------------------|---------------------------|
|
| 40 |
+
| Avg. | 53.0 |
|
| 41 |
+
| ARC (25-shot) | 63.91 |
|
| 42 |
+
| HellaSwag (10-shot) | 84.26 |
|
| 43 |
+
| MMLU (5-shot) | 62.66 |
|
| 44 |
+
| TruthfulQA (0-shot) | 53.84 |
|
| 45 |
+
| Winogrande (5-shot) | 78.22 |
|
| 46 |
+
| GSM8K (5-shot) | 19.94 |
|
| 47 |
+
| DROP (3-shot) | 8.17 |
|