|
--- |
|
language: |
|
- en |
|
--- |
|
 |
|
# MergeMonster |
|
An unsupervised merging algorithm for Transformers-based language models, using a list of phrases (both good and bad) and a fully automated strategy that strives to decrease (or increase) the probability of these phrases occurring in the final merge. |
|
|
|
[Code available here](https://github.com/Gryphe/MergeMonster/tree/main) |
|
|
|
This repo serves as a place to store various promising quantizations of merges produced by the Merge Monster. |
|
|
|
## Current variations |
|
|
|
- **MergeMonster-7b** - First model: Mistral 0.1, with the objective to reduce overused GPT style roleplaying phrases. |
|
- **MergeMonster-13b** - First model: MythoMax, with the objective to reduce overused GPT style roleplaying phrases. |
|
- **MergeMonster-Decensored-7b** - First model: Mistral 0.1, with the objective to reduce refusals on a global level. |
|
- **MergeMonster-Decensored-13b** - First model: MythoMax, with the objective to reduce refusals on a global level. |
|
- **MergeMonster-WritingStyle-7b** - First model: Mistral 0.1, with the singular goal to increase the chance of completing a nicely written roleplaying paragraph. |
