DoppelReflEx commited on
Commit
5aeb06a
·
verified ·
1 Parent(s): 971c596

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -7,18 +7,21 @@ library_name: transformers
7
  tags:
8
  - mergekit
9
  - merge
10
-
11
  ---
12
 
13
  # What is this?
14
 
15
  Next-gen version of Mimicore. Balance of roleplaying performance, intelligent and model size. I like this model, nearly 80% of my 24B MiniusLight v2.1.
16
 
 
 
 
 
17
  ## Template: Although **Mistral Tekken** one is smarter, I recommend to use *ChatML* format for roleplaying.
18
 
19
  If you don't really care about the model intelligent, ChatML is better in some cases with more creative. Mistral Tekken for smarter model, but sometimes give it a try is not too bad.
20
 
21
-
22
  ## Configuration
23
 
24
  ```yaml
@@ -41,4 +44,4 @@ tokenizer_source: base
41
  parameters:
42
  rescale: true
43
  dtype: bfloat16
44
- ```
 
7
  tags:
8
  - mergekit
9
  - merge
10
+ license: cc-by-nc-4.0
11
  ---
12
 
13
  # What is this?
14
 
15
  Next-gen version of Mimicore. Balance of roleplaying performance, intelligent and model size. I like this model, nearly 80% of my 24B MiniusLight v2.1.
16
 
17
+ ## GGUF
18
+
19
+ [Normal](https://huggingface.co/mradermacher/LilithCore-v1-12B-GGUF) - [IMatrix](https://huggingface.co/mradermacher/LilithCore-v1-12B-i1-GGUF)
20
+
21
  ## Template: Although **Mistral Tekken** one is smarter, I recommend to use *ChatML* format for roleplaying.
22
 
23
  If you don't really care about the model intelligent, ChatML is better in some cases with more creative. Mistral Tekken for smarter model, but sometimes give it a try is not too bad.
24
 
 
25
  ## Configuration
26
 
27
  ```yaml
 
44
  parameters:
45
  rescale: true
46
  dtype: bfloat16
47
+ ```