Update README.md

README.md

@@ -27,7 +27,7 @@ datasets:
 
 ## Model Description
 
-RWKV-4 trained on 100+ world languages.
+RWKV-4 trained on 100+ world languages (70% English, 15% multilang, 15% code).
 
 How to use:
 * use latest rwkv pip package (0.7.4+)
@@ -35,10 +35,10 @@ How to use:
 
 The difference between World & Raven:
 * set pipeline = PIPELINE(model, "rwkv_vocab_v20230424") instead of 20B_tokenizer.json (EXACTLY AS WRITTEN HERE. "rwkv_vocab_v20230424" is included in rwkv 0.7.4+)
-* use Question/Answer or User/AI or Human/Bot prompt. **DO NOT USE Bob/Alice or Q/A**
+* use Question/Answer or User/AI or Human/Bot prompt for Q&A. **DO NOT USE Bob/Alice or Q/A**
 * use **fp32** (will overflow in fp16 at this moment - fixable in future)
 
-NOTE: the new greedy tokenizer will tokenize '\n\n' as one single token instead of ['\n','\n']
+NOTE: the new greedy tokenizer (https://github.com/BlinkDL/ChatRWKV/blob/main/tokenizer/rwkv_tokenizer.py) will tokenize '\n\n' as one single token instead of ['\n','\n']
 
 A good prompt example:
 ```