Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,9 @@ Pros:
|
|
| 19 |
- Less repetitive (though it depends on your own prompt and settings).
|
| 20 |
- I have tested with 49444/65536 tokens no degradation although i notice it's actually learning the context better and it's impacting the output a lot. (what i don't like is, it's learning the previous context(of turns) too quickly and set it as new standards.).
|
| 21 |
|
|
|
|
|
|
|
|
|
|
| 22 |
Added note:
|
| 23 |
I was testing using my own quantization i1-Q5-K-M. i will release the full GGUF soon.
|
| 24 |
|
|
|
|
| 19 |
- Less repetitive (though it depends on your own prompt and settings).
|
| 20 |
- I have tested with 49444/65536 tokens no degradation although i notice it's actually learning the context better and it's impacting the output a lot. (what i don't like is, it's learning the previous context(of turns) too quickly and set it as new standards.).
|
| 21 |
|
| 22 |
+
Tested genres:
|
| 23 |
+
- Romance/Bromance
|
| 24 |
+
|
| 25 |
Added note:
|
| 26 |
I was testing using my own quantization i1-Q5-K-M. i will release the full GGUF soon.
|
| 27 |
|