BlinkDL
/

rwkv-4-pile-14b

Text Generation

Model card Files Files and versions Community

BlinkDL commited on Mar 5, 2023

Commit

1a3be9c

•

1 Parent(s): 89b3b19

Update README.md

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -24,6 +24,9 @@ ctx_len = 1024
 n_layer = 40
 n_embd = 5120
 Final checkpoint: RWKV-4-Pile-14B-20230213-8019.pth : Trained on the Pile for 331B tokens.
 * Pile loss 1.7579
 * LAMBADA ppl 3.81, acc 71.05%

 n_layer = 40
 n_embd = 5120
+RWKV-4-Pile-14B-2023xxxx-ctx4096-testxxx.pth : Fine-tuned to ctx_len 4096.
+* Likely better. Please test.
 Final checkpoint: RWKV-4-Pile-14B-20230213-8019.pth : Trained on the Pile for 331B tokens.
 * Pile loss 1.7579
 * LAMBADA ppl 3.81, acc 71.05%