Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -77,4 +77,17 @@ The attention mechanism in a transformer model is designed to capture global dep
|
|
| 77 |
The finetuning scripts will be available in our [RAIL Github Repository](https://github.com/vmware-labs/research-and-development-artificial-intelligence-lab/tree/main/instruction-tuning)
|
| 78 |
## Evaluation
|
| 79 |
|
| 80 |
-
<B>TODO</B>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
The finetuning scripts will be available in our [RAIL Github Repository](https://github.com/vmware-labs/research-and-development-artificial-intelligence-lab/tree/main/instruction-tuning)
|
| 78 |
## Evaluation
|
| 79 |
|
| 80 |
+
<B>TODO</B>
|
| 81 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 82 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_VMware__open-llama-7b-open-instruct)
|
| 83 |
+
|
| 84 |
+
| Metric | Value |
|
| 85 |
+
|-----------------------|---------------------------|
|
| 86 |
+
| Avg. | 40.9 |
|
| 87 |
+
| ARC (25-shot) | 49.74 |
|
| 88 |
+
| HellaSwag (10-shot) | 73.67 |
|
| 89 |
+
| MMLU (5-shot) | 31.52 |
|
| 90 |
+
| TruthfulQA (0-shot) | 34.65 |
|
| 91 |
+
| Winogrande (5-shot) | 65.43 |
|
| 92 |
+
| GSM8K (5-shot) | 0.53 |
|
| 93 |
+
| DROP (3-shot) | 30.75 |
|