PengQu commited on
Commit
15be938
1 Parent(s): 515f81a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
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
- ## 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
 
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