Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -117,4 +117,17 @@ Citation
|
|
| 117 |
YEAR = {2023},
|
| 118 |
KEYWORDS = {NLP ; Transformers ; LLM ; Bloomz},
|
| 119 |
}
|
| 120 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
YEAR = {2023},
|
| 118 |
KEYWORDS = {NLP ; Transformers ; LLM ; Bloomz},
|
| 119 |
}
|
| 120 |
+
```
|
| 121 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 122 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cmarkea__bloomz-560m-sft-chat)
|
| 123 |
+
|
| 124 |
+
| Metric | Value |
|
| 125 |
+
|-----------------------|---------------------------|
|
| 126 |
+
| Avg. | 28.49 |
|
| 127 |
+
| ARC (25-shot) | 27.47 |
|
| 128 |
+
| HellaSwag (10-shot) | 37.05 |
|
| 129 |
+
| MMLU (5-shot) | 23.93 |
|
| 130 |
+
| TruthfulQA (0-shot) | 42.35 |
|
| 131 |
+
| Winogrande (5-shot) | 53.51 |
|
| 132 |
+
| GSM8K (5-shot) | 0.0 |
|
| 133 |
+
| DROP (3-shot) | 15.13 |
|