Tarek07 commited on
Commit
a6f40e8
·
verified ·
1 Parent(s): 951c76c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -2
README.md CHANGED
@@ -12,9 +12,22 @@ library_name: transformers
12
  tags:
13
  - mergekit
14
  - merge
15
-
16
  ---
17
- # DMREMIX
 
 
 
 
 
 
 
 
 
 
 
 
 
18
 
19
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
20
 
 
12
  tags:
13
  - mergekit
14
  - merge
15
+ license: llama3.3
16
  ---
17
+ Expanded V2 of Dungeonmaster, I decided to move away from the R1 base here, because I feel it the pros dont necessarily outweigh the cons. For V2 I decided to go for the classic nbeerbower/Llama-3.1-Nemotron-lorablated-70B as the base.
18
+ Dungeonmaster expanded features 2 extra models, bringing the total up to 7! Admittedly I was concerned about that many models in one single merge. But you never know, so I decided to try both and see...
19
+
20
+ My ideal vision for Dungeonmaster were these 7 models.
21
+
22
+ LatitudeGames/Wayfarer-Large-70B-Llama-3.3 - A fine-tuned model specifically designed for this very application.
23
+ ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3 - Another fine-tune trained on RP datasets.
24
+ Sao10K/70B-L3.3-mhnnn-x1 - For some extra unhinged creativity
25
+ TheDrummer/Anubis-70B-v1 - Another excellent RP fine-tune to help balance things out.
26
+ EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1 - For it's strong descriptive writing.
27
+ SicariusSicariiStuff/Negative_LLAMA_70B - To assist with the darker undertones.
28
+ TheDrummer/Fallen-Llama-3.3-R1-70B-v1 - The secret sauce, a completely unhinged thinking model that turns things up to 11.
29
+
30
+ # Mergekit
31
 
32
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
33