Adding Evaluation Results
#10
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -67,4 +67,17 @@ sequences = pipeline(
|
|
| 67 |
)
|
| 68 |
for seq in sequences:
|
| 69 |
print(f"Result: {seq['generated_text']}")
|
| 70 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
)
|
| 68 |
for seq in sequences:
|
| 69 |
print(f"Result: {seq['generated_text']}")
|
| 70 |
+
```
|
| 71 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 72 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_PY007__TinyLlama-1.1B-step-50K-105b)
|
| 73 |
+
|
| 74 |
+
| Metric | Value |
|
| 75 |
+
|-----------------------|---------------------------|
|
| 76 |
+
| Avg. | 27.87 |
|
| 77 |
+
| ARC (25-shot) | 25.85 |
|
| 78 |
+
| HellaSwag (10-shot) | 44.1 |
|
| 79 |
+
| MMLU (5-shot) | 26.78 |
|
| 80 |
+
| TruthfulQA (0-shot) | 39.51 |
|
| 81 |
+
| Winogrande (5-shot) | 54.38 |
|
| 82 |
+
| GSM8K (5-shot) | 0.53 |
|
| 83 |
+
| DROP (3-shot) | 3.91 |
|