Update README.md
Browse files
README.md
CHANGED
@@ -18,4 +18,8 @@ datasets:
|
|
18 |
|
19 |
RWKV-2 430M is a L24-D1024 causal language model trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.
|
20 |
|
21 |
-
At this moment you have to use my Github code (https://github.com/BlinkDL/RWKV-v2-RNN-Pile) to run it.
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
RWKV-2 430M is a L24-D1024 causal language model trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.
|
20 |
|
21 |
+
At this moment you have to use my Github code (https://github.com/BlinkDL/RWKV-v2-RNN-Pile) to run it.
|
22 |
+
|
23 |
+
ctx_len = 768 n_layer = 24 n_embd = 1024
|
24 |
+
|
25 |
+
Final checkpoint: 20220615-10803.pth : Trained on the Pile for 331B tokens. Pile loss 2.349. LAMBADA ppl 15.34, acc 42.42%. PIQA acc 67.03%. SC2016 acc 62.05%. Hellaswag acc_norm 38.47%.
|