xiaol commited on
Commit
3fbf03f
1 Parent(s): 2b49697

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -8,17 +8,23 @@ finetuned for 32k context length, used to summary news article
8
 
9
  using inf-ctx training https://github.com/SynthiaDL/TrainChatGalRWKV
10
 
11
- you can test summary prompt using RWKV runner in chat mode , and check conversation files in examples folders.
12
 
13
  https://discord.gg/pWH5MkvtNR
14
 
15
  -------------------------------------------------------------------------------------------------
16
 
17
 
18
- 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,
 
 
 
 
19
 
20
  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
21
 
 
 
22
  ![微信截图_20230720145202.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/3prZb97XOKeHhVQyYevA_.png)
23
 
24
 
 
8
 
9
  using inf-ctx training https://github.com/SynthiaDL/TrainChatGalRWKV
10
 
11
+ you can test summary prompt using RWKV runner(https://github.com/josStorer/RWKV-Runner) in chat mode , and check conversation files in examples folders.
12
 
13
  https://discord.gg/pWH5MkvtNR
14
 
15
  -------------------------------------------------------------------------------------------------
16
 
17
 
18
+ 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,
19
+
20
+ 23k tokens一次性输入摘要,“Assistant:"是模型输出内容
21
+
22
+ 可以使用runner进行测试 https://github.com/josStorer/RWKV-Runner
23
 
24
  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
25
 
26
+
27
+
28
  ![微信截图_20230720145202.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/3prZb97XOKeHhVQyYevA_.png)
29
 
30