Update README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,9 @@ datasets:
|
|
6 |
---
|
7 |
We proudly announce this is the world first 128k context model based on RWKV architecture today, 2023-08-10.
|
8 |
|
|
|
|
|
|
|
9 |
This model trained with instructions datasets and chinese web novel and tradition wuxia,
|
10 |
more trainning details would be updated.
|
11 |
|
|
|
6 |
---
|
7 |
We proudly announce this is the world first 128k context model based on RWKV architecture today, 2023-08-10.
|
8 |
|
9 |
+
With RWKV world tokenizer(https://github.com/BlinkDL/ChatRWKV/blob/2a13ddecd81f8fd615b6da3a8f1091a594689e30/tokenizer/rwkv_tokenizer.py#L163) ,multi-lang has 1:1 ratio ,one word to one token.
|
10 |
+
|
11 |
+
|
12 |
This model trained with instructions datasets and chinese web novel and tradition wuxia,
|
13 |
more trainning details would be updated.
|
14 |
|