Adding Evaluation Results
#9
by
leaderboard-pr-bot
- opened
README.md
CHANGED
@@ -45,4 +45,17 @@ Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-jud
|
|
45 |
|
46 |
## Difference between different versions of Vicuna
|
47 |
|
48 |
-
See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
## Difference between different versions of Vicuna
|
47 |
|
48 |
+
See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
|
49 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
50 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_lmsys__vicuna-13b-v1.5-16k)
|
51 |
+
|
52 |
+
| Metric | Value |
|
53 |
+
|-----------------------|---------------------------|
|
54 |
+
| Avg. | 49.49 |
|
55 |
+
| ARC (25-shot) | 56.74 |
|
56 |
+
| HellaSwag (10-shot) | 80.37 |
|
57 |
+
| MMLU (5-shot) | 55.28 |
|
58 |
+
| TruthfulQA (0-shot) | 51.96 |
|
59 |
+
| Winogrande (5-shot) | 72.38 |
|
60 |
+
| GSM8K (5-shot) | 13.12 |
|
61 |
+
| DROP (3-shot) | 16.62 |
|