Gryphe commited on
Commit
1d7488a
1 Parent(s): 1e215af

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -3,13 +3,15 @@ license: other
3
  language:
4
  - en
5
  ---
6
- I received a request to upload the FP16 version of my first [MergeMonster](https://github.com/Gryphe/MergeMonster/tree/main) 13b merge, which has the sole focus of reducing overused ChatGPT roleplaying phrases.
7
 
8
  GGUF quantizations can be found in my [MergeMonster](https://huggingface.co/Gryphe/MergeMonster) repo.
9
 
10
  ## Merge Composition
11
 
12
  Unsurprisingly, not much remained of MythoMax. I'm (obviously!) very fond of it, but it's not perfect.
 
 
13
  ```
14
  Base model: MythoMax-L2-13b
15
 
 
3
  language:
4
  - en
5
  ---
6
+ I received a request to upload the FP16 version of my first [MergeMonster](https://github.com/Gryphe/MergeMonster/tree/main) 13b merge, which has the sole focus of reducing overused ChatGPT roleplaying phrases. Many ministrations were murdered throughout this process.
7
 
8
  GGUF quantizations can be found in my [MergeMonster](https://huggingface.co/Gryphe/MergeMonster) repo.
9
 
10
  ## Merge Composition
11
 
12
  Unsurprisingly, not much remained of MythoMax. I'm (obviously!) very fond of it, but it's not perfect.
13
+
14
+ Reminder: MergeMonster works with hundreds of pieces. If a model takes a large part of the composition this does not mean it is merged in a manner that might be logical to humans.
15
  ```
16
  Base model: MythoMax-L2-13b
17