Adding Evaluation Results
#12
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -82,4 +82,17 @@ These benchmarks currently have us at #1 on ARC-c, ARC-e, Hellaswag, and OpenBoo
|
|
| 82 |
## Model Usage
|
| 83 |
The model is available for download on Hugging Face. It is suitable for a wide range of language tasks, from generating creative text to understanding and following complex instructions.
|
| 84 |
|
| 85 |
-
Compute provided by our project sponsor Redmond AI, thank you!!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
## Model Usage
|
| 83 |
The model is available for download on Hugging Face. It is suitable for a wide range of language tasks, from generating creative text to understanding and following complex instructions.
|
| 84 |
|
| 85 |
+
Compute provided by our project sponsor Redmond AI, thank you!!
|
| 86 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 87 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NousResearch__Nous-Hermes-13b)
|
| 88 |
+
|
| 89 |
+
| Metric | Value |
|
| 90 |
+
|-----------------------|---------------------------|
|
| 91 |
+
| Avg. | 51.68 |
|
| 92 |
+
| ARC (25-shot) | 56.57 |
|
| 93 |
+
| HellaSwag (10-shot) | 82.11 |
|
| 94 |
+
| MMLU (5-shot) | 50.44 |
|
| 95 |
+
| TruthfulQA (0-shot) | 51.5 |
|
| 96 |
+
| Winogrande (5-shot) | 75.3 |
|
| 97 |
+
| GSM8K (5-shot) | 8.34 |
|
| 98 |
+
| DROP (3-shot) | 37.5 |
|