Commit
•
37ff722
1
Parent(s):
762ecb0
Adding Evaluation Results (#2)
Browse files- Adding Evaluation Results (3bdd5d0cf8e856673f5cef76fc39323c81efb9e4)
Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -1,4 +1,17 @@
|
|
| 1 |
CAMEL-13B-Role-Playing-Data is a chat large language model obtained by finetuning LLaMA-13B model on a total of 229K conversations created through our role-playing framework proposed in [CAMEL](https://arxiv.org/abs/2303.17760). We evaluate our model offline using EleutherAI's language model evaluation harness used by Huggingface's Open LLM Benchmark. CAMEL-13B scores an average of 57.2.
|
| 2 |
---
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
CAMEL-13B-Role-Playing-Data is a chat large language model obtained by finetuning LLaMA-13B model on a total of 229K conversations created through our role-playing framework proposed in [CAMEL](https://arxiv.org/abs/2303.17760). We evaluate our model offline using EleutherAI's language model evaluation harness used by Huggingface's Open LLM Benchmark. CAMEL-13B scores an average of 57.2.
|
| 2 |
---
|
| 3 |
license: cc-by-nc-4.0
|
| 4 |
+
---
|
| 5 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 6 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_camel-ai__CAMEL-13B-Role-Playing-Data)
|
| 7 |
+
|
| 8 |
+
| Metric | Value |
|
| 9 |
+
|-----------------------|---------------------------|
|
| 10 |
+
| Avg. | 45.03 |
|
| 11 |
+
| ARC (25-shot) | 54.95 |
|
| 12 |
+
| HellaSwag (10-shot) | 79.25 |
|
| 13 |
+
| MMLU (5-shot) | 46.61 |
|
| 14 |
+
| TruthfulQA (0-shot) | 46.35 |
|
| 15 |
+
| Winogrande (5-shot) | 74.03 |
|
| 16 |
+
| GSM8K (5-shot) | 7.35 |
|
| 17 |
+
| DROP (3-shot) | 6.66 |
|