Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -113,4 +113,17 @@ Citation
|
|
113 |
YEAR = {2023},
|
114 |
KEYWORDS = {NLP ; Transformers ; LLM ; Bloomz},
|
115 |
}
|
116 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
113 |
YEAR = {2023},
|
114 |
KEYWORDS = {NLP ; Transformers ; LLM ; Bloomz},
|
115 |
}
|
116 |
+
```
|
117 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
118 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cmarkea__bloomz-3b-sft-chat)
|
119 |
+
|
120 |
+
| Metric | Value |
|
121 |
+
|-----------------------|---------------------------|
|
122 |
+
| Avg. | 35.35 |
|
123 |
+
| ARC (25-shot) | 36.86 |
|
124 |
+
| HellaSwag (10-shot) | 54.34 |
|
125 |
+
| MMLU (5-shot) | 31.49 |
|
126 |
+
| TruthfulQA (0-shot) | 39.69 |
|
127 |
+
| Winogrande (5-shot) | 58.88 |
|
128 |
+
| GSM8K (5-shot) | 0.38 |
|
129 |
+
| DROP (3-shot) | 25.82 |
|