Hugging Face's logo

xiaol
/
rwkv-7B-world-novel-128k

Model card Files Community
2
xiaol commited on
Commit
759a8f9
•
1 Parent(s): 76e851d

Update README.md

Browse files

![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/F9unOJfhmJPXsciPHLsrl.png)

Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -9,6 +9,8 @@ We proudly announce this is the world first 128k context model based on RWKV arc
9
  This model trained with instructions datasets and chinese web novel and tradition wuxia,
10
  more trainning details would be updated.
11
 
 
 
12
  Full finetuned using this repo to train 128k context model , 4*A800 40hours with 1.3B tokens.
13
  https://github.com/SynthiaDL/TrainChatGalRWKV/blob/main/train_world.sh
14
 
@@ -26,4 +28,7 @@ Using RWKV Runner https://github.com/josStorer/RWKV-Runner to test this ， use
26
 
27
  ![QQ图片20230810143840.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/LgEjfHJ7XD7PlGM9b3RAf.png)
28
 
29
- ![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/b_6KCBdZKW7Q7HwipxE-l.png)
 
 
 
 
9
  This model trained with instructions datasets and chinese web novel and tradition wuxia,
10
  more trainning details would be updated.
11
 
12
+ Test input 67k tokens to summary ,can find in example folders ,more cases are coming.
13
+
14
  Full finetuned using this repo to train 128k context model , 4*A800 40hours with 1.3B tokens.
15
  https://github.com/SynthiaDL/TrainChatGalRWKV/blob/main/train_world.sh
16
 
 
28
 
29
  ![QQ图片20230810143840.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/LgEjfHJ7XD7PlGM9b3RAf.png)
30
 
31
+ ![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/b_6KCBdZKW7Q7HwipxE-l.png)
32
+
33
+ 67k input test
34
+ ![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/F9unOJfhmJPXsciPHLsrl.png)