Adding Evaluation Results
#28
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -112,4 +112,17 @@ This model has undergone very limited testing. Additional safety testing should
|
|
| 112 |
- **Hardware Type:** 32x A100-80GB
|
| 113 |
- **Hours used:** 480 GPU-hours
|
| 114 |
- **Cloud Provider:** AWS
|
| 115 |
-
- **Compute Region:** us-east-1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 112 |
- **Hardware Type:** 32x A100-80GB
|
| 113 |
- **Hours used:** 480 GPU-hours
|
| 114 |
- **Cloud Provider:** AWS
|
| 115 |
+
- **Compute Region:** us-east-1
|
| 116 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 117 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Phind__Phind-CodeLlama-34B-v2)
|
| 118 |
+
|
| 119 |
+
| Metric | Value |
|
| 120 |
+
|-----------------------|---------------------------|
|
| 121 |
+
| Avg. | 37.15 |
|
| 122 |
+
| ARC (25-shot) | 24.57 |
|
| 123 |
+
| HellaSwag (10-shot) | 27.6 |
|
| 124 |
+
| MMLU (5-shot) | 25.76 |
|
| 125 |
+
| TruthfulQA (0-shot) | 48.37 |
|
| 126 |
+
| Winogrande (5-shot) | 71.82 |
|
| 127 |
+
| GSM8K (5-shot) | 23.2 |
|
| 128 |
+
| DROP (3-shot) | 38.7 |
|