Update README.md
Browse files![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/5zDQVbGb-fX8Y8h98tUF0.png)
![QQ图片20230810144654.jpg](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/KjeXNjryiZjKH0PsnrE6J.jpeg)
README.md
CHANGED
@@ -1,10 +1,19 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
-
We proudly announce this is the world first 128k context model based on RWKV architecture,
|
5 |
|
6 |
This model trained with instructions datasets and chinese web novel and tradition wuxia,
|
7 |
-
more details would be updated.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
![微信截图_20230810142220.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/u2wA-l1UcW-Mt9KIoa_4q.png)
|
10 |
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
+
We proudly announce this is the world first 128k context model based on RWKV architecture today, 2023-08-10.
|
5 |
|
6 |
This model trained with instructions datasets and chinese web novel and tradition wuxia,
|
7 |
+
more trainning details would be updated.
|
8 |
+
|
9 |
+
Full finetuned using this repo to train 128k context model
|
10 |
+
https://github.com/SynthiaDL/TrainChatGalRWKV/blob/main/train_world.sh
|
11 |
+
![QQ图片20230810144654.jpg](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/KjeXNjryiZjKH0PsnrE6J.jpeg)
|
12 |
+
|
13 |
+
|
14 |
+
Using RWKV Runner https://github.com/josStorer/RWKV-Runner to test this
|
15 |
+
|
16 |
+
![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/5zDQVbGb-fX8Y8h98tUF0.png)
|
17 |
|
18 |
![微信截图_20230810142220.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/u2wA-l1UcW-Mt9KIoa_4q.png)
|
19 |
|