Adding Evaluation Results
#13
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -191,3 +191,17 @@ Apple Sillicon does not support BF16 computing, use CPU instead. (BF16 is suppor
|
|
191 |
|
192 |
The training is supported by [TPU Research Cloud](https://sites.research.google/trc/) program.
|
193 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
191 |
|
192 |
The training is supported by [TPU Research Cloud](https://sites.research.google/trc/) program.
|
193 |
|
194 |
+
|
195 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
196 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_beomi__llama-2-ko-7b)
|
197 |
+
|
198 |
+
| Metric | Value |
|
199 |
+
|-----------------------|---------------------------|
|
200 |
+
| Avg. | 39.43 |
|
201 |
+
| ARC (25-shot) | 48.46 |
|
202 |
+
| HellaSwag (10-shot) | 75.28 |
|
203 |
+
| MMLU (5-shot) | 39.56 |
|
204 |
+
| TruthfulQA (0-shot) | 34.49 |
|
205 |
+
| Winogrande (5-shot) | 72.14 |
|
206 |
+
| GSM8K (5-shot) | 1.97 |
|
207 |
+
| DROP (3-shot) | 4.1 |
|