Text Generation
PyTorch
causal-lm
rwkv
BlinkDL commited on
Commit
4ccf1d2
1 Parent(s): a6b6a11

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -34,7 +34,7 @@ How to use:
34
  * use https://github.com/BlinkDL/ChatRWKV/blob/main/v2/benchmark_world.py to test it
35
  * larger models are stronger even though not fully trained yet
36
 
37
- The difference between World & Raven:
38
  * 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+)
39
  * use Question/Answer or User/AI or Human/Bot for chat. **DO NOT USE Bob/Alice or Q/A**
40
  * use **fp32** (will overflow in fp16 at this moment - fixable in future) or bf16 (slight degradation)
 
34
  * use https://github.com/BlinkDL/ChatRWKV/blob/main/v2/benchmark_world.py to test it
35
  * larger models are stronger even though not fully trained yet
36
 
37
+ The differences between World & Raven:
38
  * 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+)
39
  * use Question/Answer or User/AI or Human/Bot for chat. **DO NOT USE Bob/Alice or Q/A**
40
  * use **fp32** (will overflow in fp16 at this moment - fixable in future) or bf16 (slight degradation)