Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: llama3
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
datasets:
|
| 4 |
+
- TigerResearch/sft_zh
|
| 5 |
+
- silk-road/alpaca-data-gpt4-chinese
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
### 模型：
|
| 9 |
+
- https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
| 10 |
+
|
| 11 |
+
### 数据集：
|
| 12 |
+
- https://huggingface.co/datasets/TigerResearch/sft_zh
|
| 13 |
+
- https://huggingface.co/datasets/silk-road/alpaca-data-gpt4-chinese
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
### 结果
|
| 17 |
+
| 模型名称 | CEVAL | MMLU |
|
| 18 |
+
|--------------------------|-------|------|
|
| 19 |
+
| LLama3 | 49.91 | 66.62|
|
| 20 |
+
| LLama3-Instruct | 50.55 | 67.15|
|
| 21 |
+
| LLama3-Instruct-sft-lora-tigerbot-alpacadatagpt4-10epoch | 53.65 | 68.09 |
|