Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,8 @@ language:
|
|
| 5 |
---
|
| 6 |
MythoMist 7b is, as always, a highly experimental Mistral-based merge based on my latest (still in development) algorithm, which actively benchmarks the model as it's being built in pursuit of a goal set by the user.
|
| 7 |
|
|
|
|
|
|
|
| 8 |
The primary purpose for MythoMist was to reduce usage of the word anticipation, ministrations and other variations we've come to associate negatively with ChatGPT roleplaying data. This algorithm cannot outright ban these words, but instead strives to minimize the usage.
|
| 9 |
|
| 10 |
I am currently in the process of cleaning up the code before publishing it, much like I did with my earlier [gradient tensor script](https://github.com/Gryphe/BlockMerge_Gradient/tree/main/YAML).
|
|
|
|
| 5 |
---
|
| 6 |
MythoMist 7b is, as always, a highly experimental Mistral-based merge based on my latest (still in development) algorithm, which actively benchmarks the model as it's being built in pursuit of a goal set by the user.
|
| 7 |
|
| 8 |
+
**Addendum (2023-11-23)**: A more thorough investigation revealed a flaw in my original algorithm that has since been resolved. I've debated deleting the model but since there are plenty of folks enjoying it I'll be keeping it around.
|
| 9 |
+
|
| 10 |
The primary purpose for MythoMist was to reduce usage of the word anticipation, ministrations and other variations we've come to associate negatively with ChatGPT roleplaying data. This algorithm cannot outright ban these words, but instead strives to minimize the usage.
|
| 11 |
|
| 12 |
I am currently in the process of cleaning up the code before publishing it, much like I did with my earlier [gradient tensor script](https://github.com/Gryphe/BlockMerge_Gradient/tree/main/YAML).
|