PengQu commited on
Commit
b415dc1
1 Parent(s): 1451ec7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -8
README.md CHANGED
@@ -21,6 +21,15 @@ 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
  ## Loading the Weights with Hugging Face Transformers
25
  See the following example for usage.
26
 
@@ -75,11 +84,4 @@ if __name__ == '__main__':
75
  python app.py
76
 
77
  ```
78
- ## Major Improvement:Llama-2-7b-vicuna-Chinese's Chinese and English abilities are better than llama2 and vicuna.
79
- - 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)
80
- - 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)
81
- - 实测效果:不会出现Llama2-chat的过于谨慎的状况
82
- <br>
83
- - English Eval results(MMLU): Llama-2-7b-vicuna-Chinese(48.8) > Llama-2-7b(45.3) > vicuna1.1(44.8)
84
- - Chinese Eval results(C-Eval): Llama-2-7b-vicuna-Chinese(34.7) > Llama-2-7b-chat(30.3)= vicuna1.1(30.3)
85
- - Empirical Results: It will not be overly cautious like Llama2-chat.
 
21
  - Finetuning data: ShareGPT,ShareGPT-ZH,Langchain-MRKL-finetune
22
  - Training code: based on [FastChat](https://github.com/lm-sys/FastChat)
23
 
24
+ ## Major Improvement:Llama-2-7b-vicuna-Chinese's Chinese and English abilities are better than llama2 and vicuna.
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
28
+ <br>
29
+ - English Eval results(MMLU): Llama-2-7b-vicuna-Chinese(48.8) > Llama-2-7b(45.3) > vicuna1.1(44.8)
30
+ - Chinese Eval results(C-Eval): Llama-2-7b-vicuna-Chinese(34.7) > Llama-2-7b-chat(30.3)= vicuna1.1(30.3)
31
+ - Empirical Results: It will not be overly cautious like Llama2-chat.
32
+
33
  ## Loading the Weights with Hugging Face Transformers
34
  See the following example for usage.
35
 
 
84
  python app.py
85
 
86
  ```
87
+