Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,8 @@ datasets:
|
|
| 18 |
|
| 19 |
RWKV-4 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-LM) to run it.
|
| 22 |
|
| 23 |
ctx_len = 1024
|
|
|
|
| 18 |
|
| 19 |
RWKV-4 430M is a L24-D1024 causal language model trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.
|
| 20 |
|
| 21 |
+
** Note: It's a BF16 model, and it may overflow if you are using FP16 (probably fixable by rescaling the weights). **
|
| 22 |
+
|
| 23 |
At this moment you have to use my Github code (https://github.com/BlinkDL/RWKV-LM) to run it.
|
| 24 |
|
| 25 |
ctx_len = 1024
|