Commit
•
8e01116
1
Parent(s):
39c1c68
Adding Evaluation Results (#3)
Browse files- Adding Evaluation Results (937fe2600f0823f034dbe811b07d5ba74c38017b)
Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>
README.md
CHANGED
|
@@ -70,3 +70,17 @@ tokenizer.batch_decode(generate_ids)[0]
|
|
| 70 |
```
|
| 71 |
|
| 72 |
To utilize the prompt format without a system prompt, simply leave the line out.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
```
|
| 71 |
|
| 72 |
To utilize the prompt format without a system prompt, simply leave the line out.
|
| 73 |
+
|
| 74 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 75 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_orangetin__OpenHermes-Mixtral-8x7B)
|
| 76 |
+
|
| 77 |
+
| Metric |Value|
|
| 78 |
+
|---------------------------------|----:|
|
| 79 |
+
|Avg. |65.27|
|
| 80 |
+
|AI2 Reasoning Challenge (25-Shot)|63.91|
|
| 81 |
+
|HellaSwag (10-Shot) |84.14|
|
| 82 |
+
|MMLU (5-Shot) |64.29|
|
| 83 |
+
|TruthfulQA (0-shot) |59.53|
|
| 84 |
+
|Winogrande (5-shot) |74.03|
|
| 85 |
+
|GSM8k (5-shot) |45.72|
|
| 86 |
+
|