Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
-
|
2 |
|
3 |
I also converted original weights back to fp32 before quantization.
|
|
|
1 |
+
Should be working properly with KoboldCPP and other stuff. I changed EOS token to <|eot_id|> and this prevents endless generation.
|
2 |
|
3 |
I also converted original weights back to fp32 before quantization.
|