Update README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ Llama-2-7b-vicuna-Chinese is a chat model supervised finetuned on vicuna sharegp
|
|
21 |
- Finetuning data: ShareGPT,ShareGPT-ZH,Langchain-MRKL-finetune
|
22 |
- Training code: based on [FastChat](https://github.com/lm-sys/FastChat)
|
23 |
|
24 |
-
|
25 |
- 英语能力基础评测(MMLU): Llama-2-7b-vicuna-Chinese(48.8) > Llama-2-7b(45.3) > vicuna1.1(44.8)
|
26 |
- 中文能力基础评测(C-Eval): Llama-2-7b-vicuna-Chinese(34.7) > Llama-2-7b-chat(30.3)= vicuna1.1(30.3)
|
27 |
- 实测效果:不会出现Llama2-chat的过于谨慎的状况
|
|
|
21 |
- Finetuning data: ShareGPT,ShareGPT-ZH,Langchain-MRKL-finetune
|
22 |
- Training code: based on [FastChat](https://github.com/lm-sys/FastChat)
|
23 |
|
24 |
+
#### 主要改进:中英能力相比Llama2原版和vicuna均有提升
|
25 |
- 英语能力基础评测(MMLU): Llama-2-7b-vicuna-Chinese(48.8) > Llama-2-7b(45.3) > vicuna1.1(44.8)
|
26 |
- 中文能力基础评测(C-Eval): Llama-2-7b-vicuna-Chinese(34.7) > Llama-2-7b-chat(30.3)= vicuna1.1(30.3)
|
27 |
- 实测效果:不会出现Llama2-chat的过于谨慎的状况
|