Adding Evaluation Results
#94
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -233,4 +233,17 @@ To learn more about the pretraining dataset, see the 📓 [RefinedWeb paper](htt
|
|
| 233 |
Falcon-7B is made available under the Apache 2.0 license.
|
| 234 |
|
| 235 |
## Contact
|
| 236 |
-
falconllm@tii.ae
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 233 |
Falcon-7B is made available under the Apache 2.0 license.
|
| 234 |
|
| 235 |
## Contact
|
| 236 |
+
falconllm@tii.ae
|
| 237 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 238 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_tiiuae__falcon-7b)
|
| 239 |
+
|
| 240 |
+
| Metric | Value |
|
| 241 |
+
|-----------------------|---------------------------|
|
| 242 |
+
| Avg. | 38.27 |
|
| 243 |
+
| ARC (25-shot) | 47.87 |
|
| 244 |
+
| HellaSwag (10-shot) | 78.13 |
|
| 245 |
+
| MMLU (5-shot) | 27.79 |
|
| 246 |
+
| TruthfulQA (0-shot) | 34.26 |
|
| 247 |
+
| Winogrande (5-shot) | 72.38 |
|
| 248 |
+
| GSM8K (5-shot) | 2.65 |
|
| 249 |
+
| DROP (3-shot) | 4.82 |
|