Adding Evaluation Results
#6
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -193,4 +193,17 @@ Please refer to our [blog post](https://together.xyz) for benchmark results.
|
|
193 |
|
194 |
## Community
|
195 |
|
196 |
-
Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
193 |
|
194 |
## Community
|
195 |
|
196 |
+
Join us on [Together Discord](https://discord.gg/6ZVDU8tTD4)
|
197 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
198 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_togethercomputer__RedPajama-INCITE-Base-3B-v1)
|
199 |
+
|
200 |
+
| Metric | Value |
|
201 |
+
|-----------------------|---------------------------|
|
202 |
+
| Avg. | 33.73 |
|
203 |
+
| ARC (25-shot) | 40.19 |
|
204 |
+
| HellaSwag (10-shot) | 64.77 |
|
205 |
+
| MMLU (5-shot) | 27.03 |
|
206 |
+
| TruthfulQA (0-shot) | 33.23 |
|
207 |
+
| Winogrande (5-shot) | 64.72 |
|
208 |
+
| GSM8K (5-shot) | 1.29 |
|
209 |
+
| DROP (3-shot) | 4.9 |
|