---
license: apache-2.0
---

This is full finetune model from RWKV 4 world 7B CHNTuned using data from Readflow tech (readflow.com.cn) ,

finetuned for  32k context length, used to summary news article

using inf-ctx training https://github.com/SynthiaDL/TrainChatGalRWKV

you can test summary prompt using RWKV runner in chat mode , and check conversation files in examples folders.

https://discord.gg/pWH5MkvtNR

-------------------------------------------------------------------------------------------------


这是和会读Readflow合作的模型（ readflow.com.cn），用于超长微信文章的摘要，训练了32k的context长度，能一次性输入整篇文章进行摘要，如下图以及在example文件夹中的例子，23k tokens一次性输入摘要，

RWKV world的token对中文以及各类语言效率很高，token和字比例，基本是1:1,甚至1:n，欢迎测试，并加入微调QQ群讨论439087067

![微信截图_20230720145202.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/3prZb97XOKeHhVQyYevA_.png)