Adding Evaluation Results
#2
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -1,4 +1,17 @@
|
|
| 1 |
Experimental mythomax based ERP model.
|
| 2 |
Use Alpaca format, merged models: mythomax, puddlejumper, airoboros, chronos beluga
|
| 3 |
|
| 4 |
-
gguf here: https://huggingface.co/TheBloke/Athena-v1-GGUF
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
Experimental mythomax based ERP model.
|
| 2 |
Use Alpaca format, merged models: mythomax, puddlejumper, airoboros, chronos beluga
|
| 3 |
|
| 4 |
+
gguf here: https://huggingface.co/TheBloke/Athena-v1-GGUF
|
| 5 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 6 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_IkariDev__Athena-v1)
|
| 7 |
+
|
| 8 |
+
| Metric | Value |
|
| 9 |
+
|-----------------------|---------------------------|
|
| 10 |
+
| Avg. | 52.68 |
|
| 11 |
+
| ARC (25-shot) | 60.07 |
|
| 12 |
+
| HellaSwag (10-shot) | 82.64 |
|
| 13 |
+
| MMLU (5-shot) | 55.61 |
|
| 14 |
+
| TruthfulQA (0-shot) | 46.58 |
|
| 15 |
+
| Winogrande (5-shot) | 74.82 |
|
| 16 |
+
| GSM8K (5-shot) | 4.93 |
|
| 17 |
+
| DROP (3-shot) | 44.11 |
|