BlinkDL commited on
Commit
1b3f6b8
1 Parent(s): ce7047c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -25,7 +25,7 @@ datasets:
25
 
26
  # RWKV-5 World (Training in Progress)
27
 
28
- Use https://huggingface.co/BlinkDL/rwkv-4-world for best models. I am still training RWKV-5.
29
 
30
  Use rwkv pip package 0.8.7+ for RWKV-5 inference.
31
 
@@ -35,9 +35,9 @@ RWKV-5 trained on 100+ world languages (70% English, 15% multilang, 15% code).
35
 
36
  World = Some_Pile + Some_RedPajama + Some_OSCAR + All_Wikipedia + All_ChatGPT_Data_I_can_find
37
 
38
- Training: set --my_testing "r" for latest RWKV-LM
39
 
40
- Inference algorithm reference: https://github.com/BlinkDL/ChatRWKV/blob/main/RWKV_v5_demo.py
41
 
42
  0.1B world:
43
 
 
25
 
26
  # RWKV-5 World (Training in Progress)
27
 
28
+ Note https://huggingface.co/BlinkDL/rwkv-4-world are the best models as of now, because I am still training RWKV-5.
29
 
30
  Use rwkv pip package 0.8.7+ for RWKV-5 inference.
31
 
 
35
 
36
  World = Some_Pile + Some_RedPajama + Some_OSCAR + All_Wikipedia + All_ChatGPT_Data_I_can_find
37
 
38
+ RWKV-5 training: set --my_testing "r" in latest RWKV-LM
39
 
40
+ RWKV-5 inference implementation reference: https://github.com/BlinkDL/ChatRWKV/blob/main/RWKV_v5_demo.py
41
 
42
  0.1B world:
43