Commit
•
348d956
1
Parent(s):
2711d02
Update README.md
Browse files
README.md
CHANGED
@@ -12,3 +12,18 @@ This is yet another mergekit abomination.
|
|
12 |
Still undergoing testing.
|
13 |
|
14 |
This is probably more of a "dense" MoE than a sparse one.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
Still undergoing testing.
|
13 |
|
14 |
This is probably more of a "dense" MoE than a sparse one.
|
15 |
+
|
16 |
+
|
17 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
18 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lodrick-the-lafted__Winged-Lagomorph-2x13B)
|
19 |
+
|
20 |
+
| Metric |Value|
|
21 |
+
|---------------------------------|----:|
|
22 |
+
|Avg. |73.77|
|
23 |
+
|AI2 Reasoning Challenge (25-Shot)|72.61|
|
24 |
+
|HellaSwag (10-Shot) |89.57|
|
25 |
+
|MMLU (5-Shot) |71.67|
|
26 |
+
|TruthfulQA (0-shot) |66.49|
|
27 |
+
|Winogrande (5-shot) |84.37|
|
28 |
+
|GSM8k (5-shot) |57.92|
|
29 |
+
|