Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -13,4 +13,17 @@ use alpaca format? maybe.
|
|
13 |
|
14 |
> TheBloke GGUF and GPTQ:\
|
15 |
> https://huggingface.co/TheBloke/AppleSauce-L2-13B-GGUF \
|
16 |
-
> https://huggingface.co/TheBloke/AppleSauce-L2-13B-GPTQ
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
> TheBloke GGUF and GPTQ:\
|
15 |
> https://huggingface.co/TheBloke/AppleSauce-L2-13B-GGUF \
|
16 |
+
> https://huggingface.co/TheBloke/AppleSauce-L2-13B-GPTQ
|
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_sauce1337__AppleSauce-L2-13b)
|
19 |
+
|
20 |
+
| Metric | Value |
|
21 |
+
|-----------------------|---------------------------|
|
22 |
+
| Avg. | 54.37 |
|
23 |
+
| ARC (25-shot) | 61.01 |
|
24 |
+
| HellaSwag (10-shot) | 83.61 |
|
25 |
+
| MMLU (5-shot) | 57.07 |
|
26 |
+
| TruthfulQA (0-shot) | 47.81 |
|
27 |
+
| Winogrande (5-shot) | 75.93 |
|
28 |
+
| GSM8K (5-shot) | 10.01 |
|
29 |
+
| DROP (3-shot) | 45.19 |
|