Update README.md
Browse files
README.md
CHANGED
@@ -12,6 +12,18 @@ tags:
|
|
12 |
|
13 |
Lumina-3.5 is a Mixture of Experts (MoE) made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing). This model uses a context window of up to 32k.
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
## 💻 Usage
|
16 |
|
17 |
```python
|
|
|
12 |
|
13 |
Lumina-3.5 is a Mixture of Experts (MoE) made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing). This model uses a context window of up to 32k.
|
14 |
|
15 |
+
## 🏆 Open LLM Leaderboard Evaluation Results
|
16 |
+
|
17 |
+
| Metric |Value|
|
18 |
+
|---------------------------------|----:|
|
19 |
+
|Avg. |75.41|
|
20 |
+
|AI2 Reasoning Challenge (25-Shot)|71.59|
|
21 |
+
|HellaSwag (10-Shot) |88.82|
|
22 |
+
|MMLU (5-Shot) |64.48|
|
23 |
+
|TruthfulQA (0-shot) |75.66|
|
24 |
+
|Winogrande (5-shot) |83.98|
|
25 |
+
|GSM8k (5-shot) |67.93|
|
26 |
+
|
27 |
## 💻 Usage
|
28 |
|
29 |
```python
|