Adding Evaluation Results
#2
by leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -68,3 +68,17 @@ hf-causal-experimental (pretrained=winglian/basilisk-4b,use_accelerate=True,trus
|
|
| 68 |
| | |acc_norm|0.6921|_ |0.0108|
|
| 69 |
|winogrande | 0|acc |0.5399|_ |0.0140|
|
| 70 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
| | |acc_norm|0.6921|_ |0.0108|
|
| 69 |
|winogrande | 0|acc |0.5399|_ |0.0140|
|
| 70 |
```
|
| 71 |
+
|
| 72 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 73 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_winglian__basilisk-4b)
|
| 74 |
+
|
| 75 |
+
| Metric | Value |
|
| 76 |
+
|-----------------------|---------------------------|
|
| 77 |
+
| Avg. | 27.26 |
|
| 78 |
+
| ARC (25-shot) | 25.85 |
|
| 79 |
+
| HellaSwag (10-shot) | 39.6 |
|
| 80 |
+
| MMLU (5-shot) | 24.61 |
|
| 81 |
+
| TruthfulQA (0-shot) | 43.74 |
|
| 82 |
+
| Winogrande (5-shot) | 53.12 |
|
| 83 |
+
| GSM8K (5-shot) | 0.0 |
|
| 84 |
+
| DROP (3-shot) | 3.89 |
|