Update README.md

README.md

@@ -20,16 +20,11 @@ RWKV-4 14B is a L40-D5120 causal language model trained on the Pile. See https:/
 
 Use https://github.com/BlinkDL/ChatRWKV to run it.
 
-n_layer = 40
-n_embd = 5120
-
 RWKV-4-Pile-14B-2023xxxx-ctx4096-testxxx.pth : Fine-tuned to ctx_len 4096.
-* ctx_len = 4096
 * Highly recommended. It's great.
 
-RWKV-4-Pile-14B-20230213-8019.pth : Trained on the Pile for 331B tokens.
-* ctx_len = 1024
-* Pile loss 1.7579
+RWKV-4-Pile-14B-20230213-8019.pth : Trained on the Pile for 331B tokens
+* Pile loss 1.7579 (ctx_len 1024)
 * LAMBADA ppl 3.81, acc 71.05%
 * PIQA acc 77.42%
 * SC2016 acc 75.57%