Merge branch 'main' of github.com:Abbey4799/CuteGPT

Abbey4799 · Jul 3, 2023 · f59da1e · f59da1e
2 parents 70030fd 2141fcc
commit f59da1e
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -2,13  2,13 @@
 
 [[Readme ENG](README.md)][[Readme ZH](README_ch.md)]
 
-CuteGPT is an open-source conversational language model that supports both Chinese and English, developed by [Fudan University Knowledge Workshop Laboratory](http://kw.fudan.edu.cn/). It is based on the original Llama model structure, and has a scale of 13B (13 billion) parameters. It can perform int8 precision inference on a single 3090 graphics card. CuteGPT expands the Chinese vocabulary and performs pre-training on the Llama model, improving its ability to understand Chinese. Subsequently, it is fine-tuned with conversational instructions to enhance the model's ability to understand instructions.
 CuteGPT is an open-source conversational language model that supports both Chinese and English, developed by [Fudan University KnowledgeWorks Laboratory](http://kw.fudan.edu.cn/). It is based on the original Llama model structure, and has a scale of 13B (13 billion) parameters. It can perform int8 precision inference on a single 3090 graphics card. CuteGPT expands the Chinese vocabulary and performs pre-training on the Llama model, improving its ability to understand Chinese. Subsequently, it is fine-tuned with conversational instructions to enhance the model's ability to understand instructions.
 
 ## Open Parameters
 
 | Huggingface                       | Description                                                                              |
 | --------------------------------- | ---------------------------------------------------------------------------------------- |
-| XuYipei/kw-cutegpt-13b-base       | Expand Chinese vocabulary and perform secondary pre-training based on the original Llama |
 | XuYipei/kw-cutegpt-13b-base       | Expand Chinese vocabulary and perform pre-training                              |
 | XuYipei/kw-cutegpt-13b-ift        | Full parameter instruction fine-tuning                                                   |
 | Abbey4799/kw-cutegpt-13b-ift-lora | Instruction fine-tuning based on lora                                                    |
 

diff --git a/README_ch.md b/README_ch.md
@@ -8,7  8,7 @@ CuteGPT是[复旦大学知识工场实验室](http://kw.fudan.edu.cn/)推出的
 
 | Huggingface                       | 描述                                      |
 | --------------------------------- | ----------------------------------------- |
-| XuYipei/kw-cutegpt-13b-base       | 基于原版Llama扩充中文词表并进行二次预训练 |
 | XuYipei/kw-cutegpt-13b-base       | 基于扩充中文词表进行预训练                |
 | XuYipei/kw-cutegpt-13b-ift        | 全量参数指令微调                          |
 | Abbey4799/kw-cutegpt-13b-ift-lora | 基于lora指令微调                          |