Add community evaluation results for GPQA, MMLU-PRO
#1
by nielsr HF Staff - opened
- .eval_results/gpqa.yaml +7 -0
- .eval_results/mmlu-pro.yaml +7 -0
.eval_results/gpqa.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: Idavidrein/gpqa
|
| 3 |
+
task_id: diamond
|
| 4 |
+
value: 71
|
| 5 |
+
source:
|
| 6 |
+
url: https://huggingface.co/Zyphra/ZAYA1-8B
|
| 7 |
+
name: Model Card
|
.eval_results/mmlu-pro.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: TIGER-Lab/MMLU-Pro
|
| 3 |
+
task_id: mmlu_pro
|
| 4 |
+
value: 74.2
|
| 5 |
+
source:
|
| 6 |
+
url: https://huggingface.co/Zyphra/ZAYA1-8B
|
| 7 |
+
name: Model Card
|