Adding Evaluation Results
#1
by
leaderboard-pr-bot - opened
README.md
CHANGED
|
@@ -22,4 +22,17 @@ Refer to [ToolBench](https://github.com/OpenBMB/ToolBench).
|
|
| 22 |
|
| 23 |
## Training Details
|
| 24 |
|
| 25 |
-
Trained with the new version data in ToolBench.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Training Details
|
| 24 |
|
| 25 |
+
Trained with the new version data in ToolBench.
|
| 26 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 27 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ToolBench__ToolLLaMA-7b-LoRA)
|
| 28 |
+
|
| 29 |
+
| Metric | Value |
|
| 30 |
+
|-----------------------|---------------------------|
|
| 31 |
+
| Avg. | 43.42 |
|
| 32 |
+
| ARC (25-shot) | 52.99 |
|
| 33 |
+
| HellaSwag (10-shot) | 78.62 |
|
| 34 |
+
| MMLU (5-shot) | 46.87 |
|
| 35 |
+
| TruthfulQA (0-shot) | 38.67 |
|
| 36 |
+
| Winogrande (5-shot) | 74.35 |
|
| 37 |
+
| GSM8K (5-shot) | 6.82 |
|
| 38 |
+
| DROP (3-shot) | 5.61 |
|