Text Generation
PyTorch
causal-lm
rwkv
BlinkDL commited on
Commit
dc9a0eb
1 Parent(s): 06dc12e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -33,7 +33,8 @@ How to use:
33
  * use latest rwkv pip package (0.7.4+)
34
  * use latest ChatRWKV v2/chat.py
35
  * 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+)
36
- * Use Q/A or User/AI or Human/Bot prompt, instead of Bob/Alice
 
37
 
38
  Example:
39
  ```
 
33
  * use latest rwkv pip package (0.7.4+)
34
  * use latest ChatRWKV v2/chat.py
35
  * 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+)
36
+ * use Q/A or User/AI or Human/Bot prompt, instead of Bob/Alice
37
+ * use fp32 (will overflow in fp16 at this moment - fixable in future)
38
 
39
  Example:
40
  ```