Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -10,4 +10,17 @@ pipeline_tag: question-answering
|
|
| 10 |
---
|
| 11 |
|
| 12 |
bimoGPT - 一个在llama2 13b基座模型上做中文精细SFT的版本，拥有接近ChatGPT的语气和对话问答能力，以及不错的代码编程能力。
|
| 13 |
-
底座：https://www.codewithgpu.com/m/file/llama2-13b-Chinese-chat (中的llama2-13B-sharegpt_cn-epoch2.zip)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
bimoGPT - 一个在llama2 13b基座模型上做中文精细SFT的版本，拥有接近ChatGPT的语气和对话问答能力，以及不错的代码编程能力。
|
| 13 |
+
底座：https://www.codewithgpu.com/m/file/llama2-13b-Chinese-chat (中的llama2-13B-sharegpt_cn-epoch2.zip)
|
| 14 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 15 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_shareAI__bimoGPT-llama2-13b)
|
| 16 |
+
|
| 17 |
+
| Metric | Value |
|
| 18 |
+
|-----------------------|---------------------------|
|
| 19 |
+
| Avg. | 46.84 |
|
| 20 |
+
| ARC (25-shot) | 58.79 |
|
| 21 |
+
| HellaSwag (10-shot) | 82.08 |
|
| 22 |
+
| MMLU (5-shot) | 55.6 |
|
| 23 |
+
| TruthfulQA (0-shot) | 37.82 |
|
| 24 |
+
| Winogrande (5-shot) | 76.48 |
|
| 25 |
+
| GSM8K (5-shot) | 11.3 |
|
| 26 |
+
| DROP (3-shot) | 5.84 |
|