Hugging Face's logo

BlinkDL
/
rwkv-4-pile-14b

Text Generation
PyTorch
English
causal-lm
rwkv
Model card Files Community
2
BlinkDL commited on
Commit
f06804d
•
1 Parent(s): 82ae7ee

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -4
README.md CHANGED
@@ -24,10 +24,7 @@ args.n_embd = 5120
24
  Use https://github.com/BlinkDL/ChatRWKV to run it.
25
 
26
  RWKV-4-Pile-14B-2023xxxx-ctx8192-testxxx.pth : Fine-tuned to ctx_len 8192.
27
- * The best.
28
-
29
- RWKV-4-Pile-14B-2023xxxx-ctx4096-testxxx.pth : Fine-tuned to ctx_len 4096.
30
- * Highly recommended. It's great.
31
 
32
  RWKV-4-Pile-14B-20230213-8019.pth : Trained on the Pile for 331B tokens
33
  * Pile loss 1.7579 (ctx_len 1024)
 
24
  Use https://github.com/BlinkDL/ChatRWKV to run it.
25
 
26
  RWKV-4-Pile-14B-2023xxxx-ctx8192-testxxx.pth : Fine-tuned to ctx_len 8192.
27
+ * The best model.
 
 
 
28
 
29
  RWKV-4-Pile-14B-20230213-8019.pth : Trained on the Pile for 331B tokens
30
  * Pile loss 1.7579 (ctx_len 1024)