gnh1201/Open-Llama
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
LiangSong 2023-05-14 10:48:49 +08:00
parent a07d9b0ac8
commit 52e8df9a8d
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -2,7 +2,7 @@
* @Author: LiangSong(sl12160010@gmail.com) * @Author: LiangSong(sl12160010@gmail.com)
* @Date: 2023-03-10 21:18:35 * @Date: 2023-03-10 21:18:35
* @LastEditors: LiangSong(sl12160010@gmail.com) * @LastEditors: LiangSong(sl12160010@gmail.com)
* @LastEditTime: 2023-05-14 01:05:56 * @LastEditTime: 2023-05-14 10:48:34
* @FilePath: /Open-Llama/README.md * @FilePath: /Open-Llama/README.md
* @Description: * @Description:
* *
@ -27,7 +27,7 @@ Open-Llama is an open-source project that offers a complete training pipeline fo
- **Support Transformers/HuggingFace.** The CheckPoint after Instruct-tuning is open-source on [HuggingFace: s-JoL/Open-Llama-V2](https://huggingface.co/s-JoL/Open-Llama-V2). - **Support Transformers/HuggingFace.** The CheckPoint after Instruct-tuning is open-source on [HuggingFace: s-JoL/Open-Llama-V2](https://huggingface.co/s-JoL/Open-Llama-V2).
- **By adopting the same evaluation method as the FastChat project, Open-Llama's performance is compared to GPT3.5’s. After testing, it can reach 84% of GPT3.5's performance on Chinese questions.** - **By adopting the same evaluation method as the FastChat project, Open-Llama's performance is compared to GPT3.5’s. After testing, it can reach 89% of GPT3.5's performance on Chinese questions.**
- **The training speed reaches 3620 tokens/s, faster than the 3370 tokens/s reported in the original Llama paper, reaching the current state-of-the-art level.** - **The training speed reaches 3620 tokens/s, faster than the 3370 tokens/s reported in the original Llama paper, reaching the current state-of-the-art level.**

4
README_zh.md
View File

@ -2,7 +2,7 @@
* @Author: LiangSong(sl12160010@gmail.com) * @Author: LiangSong(sl12160010@gmail.com)
* @Date: 2023-03-10 21:18:35 * @Date: 2023-03-10 21:18:35
* @LastEditors: LiangSong(sl12160010@gmail.com) * @LastEditors: LiangSong(sl12160010@gmail.com)
* @LastEditTime: 2023-05-14 01:05:25 * @LastEditTime: 2023-05-14 10:48:43
* @FilePath: /Open-Llama/README_zh.md * @FilePath: /Open-Llama/README_zh.md
* @Description: * @Description:
* *
@ -27,7 +27,7 @@ Open-Llama是一个开源项目，提供了一整套用于构建大型语言模
- **支持Transformers/HuggingFace直接调用。** 经过Instruct-tuning的CheckPoint已开源在[HuggingFace: s-JoL/Open-Llama-V2](https://huggingface.co/s-JoL/Open-Llama-V2)。 - **支持Transformers/HuggingFace直接调用。** 经过Instruct-tuning的CheckPoint已开源在[HuggingFace: s-JoL/Open-Llama-V2](https://huggingface.co/s-JoL/Open-Llama-V2)。
- **采用FastChat项目相同方法测评Open-Llama的效果和GPT3.5的效果对比，经过测试在中文问题上可以达到GPT3.5 84%的水平。** - **采用FastChat项目相同方法测评Open-Llama的效果和GPT3.5的效果对比，经过测试在中文问题上可以达到GPT3.5 89%的水平。**
- **训练速度达到3620 token/s，快于Llama原文中的3370 token/s，达到目前sota的水平。** - **训练速度达到3620 token/s，快于Llama原文中的3370 token/s，达到目前sota的水平。**