Update README.md
Browse files
README.md
CHANGED
|
@@ -40,4 +40,6 @@ Vision is present. Works, but vision isn't my thing so i can't tell more.
|
|
| 40 |
I've noticed a small repetition problem when the model gives one long answer. (The context becomes poisoned by a long, monotonous answer, and because of the excellent attention, the model starts to repeat itself more and more.) It's probably fixable with a repetition penalty setting, but I haven't figured out the sweet spot where it works without breaking the response too much.
|
| 41 |
On shorter answers this problem didn't occured.
|
| 42 |
|
| 43 |
-
Tested on the GemmaT4 preset, modified Shingane sysprompt T0.8 - 1.04 for roleplaying; a custom assistant sysprompt, T0.21 for work.
|
|
|
|
|
|
|
|
|
| 40 |
I've noticed a small repetition problem when the model gives one long answer. (The context becomes poisoned by a long, monotonous answer, and because of the excellent attention, the model starts to repeat itself more and more.) It's probably fixable with a repetition penalty setting, but I haven't figured out the sweet spot where it works without breaking the response too much.
|
| 41 |
On shorter answers this problem didn't occured.
|
| 42 |
|
| 43 |
+
Tested on the GemmaT4 preset, modified Shingane sysprompt T0.8 - 1.04 for roleplaying; a custom assistant sysprompt, T0.21 for work.
|
| 44 |
+
|
| 45 |
+
Also tested by chance on rx 6600xt and on gtx 1060 6gb (with offload ofc), it works and speed was even bearable.
|