Update README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,7 @@ With RWKV world tokenizer,multi-langs have 1:1 tokenization ratio ,one word to o
|
|
14 |
This model trained with instructions datasets and chinese web novel and tradition wuxia,
|
15 |
more trainning details would be updated.
|
16 |
|
17 |
-
Test input
|
18 |
|
19 |
Full finetuned using this repo to train 128k context model , 4*A800 40hours with 1.3B tokens.
|
20 |
https://github.com/SynthiaDL/TrainChatGalRWKV/blob/main/train_world.sh
|
@@ -35,7 +35,7 @@ Using RWKV Runner https://github.com/josStorer/RWKV-Runner to test this , use
|
|
35 |
|
36 |
![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/b_6KCBdZKW7Q7HwipxE-l.png)
|
37 |
|
38 |
-
|
39 |
![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/F9unOJfhmJPXsciPHLsrl.png)
|
40 |
|
41 |
![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/35j5C1QD_4cO-AjfxV7tl.png)
|
|
|
14 |
This model trained with instructions datasets and chinese web novel and tradition wuxia,
|
15 |
more trainning details would be updated.
|
16 |
|
17 |
+
Test input 85k tokens to summary ,can find conversation files in example folders ,more cases are coming.
|
18 |
|
19 |
Full finetuned using this repo to train 128k context model , 4*A800 40hours with 1.3B tokens.
|
20 |
https://github.com/SynthiaDL/TrainChatGalRWKV/blob/main/train_world.sh
|
|
|
35 |
|
36 |
![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/b_6KCBdZKW7Q7HwipxE-l.png)
|
37 |
|
38 |
+
85k input test
|
39 |
![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/F9unOJfhmJPXsciPHLsrl.png)
|
40 |
|
41 |
![image.png](https://cdn-uploads.huggingface.co/production/uploads/6176b32847ee6431f632981e/35j5C1QD_4cO-AjfxV7tl.png)
|