Add Open LLM Leaderboard results
Browse files
README.md
CHANGED
|
@@ -15,7 +15,6 @@ base_model:
|
|
| 15 |
|
| 16 |
Due to [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) updating its license to CC-BY-NC, our license will follow suit.
|
| 17 |
|
| 18 |
-
|
| 19 |
# Model Description
|
| 20 |
|
| 21 |
This is an experiment to test merging 14 models using DARE TIES 🦙
|
|
@@ -26,6 +25,17 @@ This is an experiment to test merging 14 models using DARE TIES 🦙
|
|
| 26 |
- [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
|
| 27 |
- [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B)
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
## Chat Template
|
| 30 |
|
| 31 |
Either ChatML or Llama-2 chat template.
|
|
|
|
| 15 |
|
| 16 |
Due to [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) updating its license to CC-BY-NC, our license will follow suit.
|
| 17 |
|
|
|
|
| 18 |
# Model Description
|
| 19 |
|
| 20 |
This is an experiment to test merging 14 models using DARE TIES 🦙
|
|
|
|
| 25 |
- [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
|
| 26 |
- [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B)
|
| 27 |
|
| 28 |
+
## Open LLM Leaderboard
|
| 29 |
+
|
| 30 |
+
| Average | 71.96 |
|
| 31 |
+
|------------|-------|
|
| 32 |
+
| ARC | 68.69 |
|
| 33 |
+
| HellaSwag | 86.45 |
|
| 34 |
+
| MMLU | 65.65 |
|
| 35 |
+
| TruthfulQA | 59.12 |
|
| 36 |
+
| Winogrande | 80.66 |
|
| 37 |
+
| GSM8K | 71.19 |
|
| 38 |
+
|
| 39 |
## Chat Template
|
| 40 |
|
| 41 |
Either ChatML or Llama-2 chat template.
|