nbeerbower commited on
Commit
d740b72
1 Parent(s): 465cfd8

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ mahou-1.5-mistral-nemo-12b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ mahou-1.5-mistral-nemo-12b.bf16.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - flammenai/Flammades-Mistral-Nemo-12B
4
+ datasets:
5
+ - flammenai/MahouMix-v1
6
+ library_name: transformers
7
+ license: apache-2.0
8
+ tags:
9
+ - autoquant
10
+ - gguf
11
+ ---
12
+ ![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png)
13
+
14
+ # Mahou-1.5-mistral-nemo-12B
15
+
16
+ Mahou is designed to provide short messages in a conversational context. It is capable of casual conversation and character roleplay.
17
+
18
+ ### Chat Format
19
+
20
+ This model has been trained to use ChatML format.
21
+
22
+ ```
23
+ <|im_start|>system
24
+ {{system}}<|im_end|>
25
+ <|im_start|>{{char}}
26
+ {{message}}<|im_end|>
27
+ <|im_start|>{{user}}
28
+ {{message}}<|im_end|>
29
+ ```
30
+
31
+ ### Roleplay Format
32
+
33
+ - Speech without quotes.
34
+ - Actions in `*asterisks*`
35
+
36
+ ```
37
+ *leans against wall cooly* so like, i just casted a super strong spell at magician academy today, not gonna lie, felt badass.
38
+ ```
39
+
40
+ ### SillyTavern Settings
41
+
42
+ 1. Use ChatML for the Context Template.
43
+ 2. Enable Instruct Mode.
44
+ 3. Use the [Mahou ChatML Instruct preset](https://huggingface.co/datasets/flammenai/Mahou-ST-ChatML-Instruct/raw/main/Mahou.json).
45
+ 4. Use the [Mahou Sampler preset](https://huggingface.co/datasets/flammenai/Mahou-ST-Sampler-Preset/raw/main/Mahou.json).
46
+
47
+ ### Method
48
+
49
+ [ORPO finetuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 4x H100 for 3 epochs.
mahou-1.5-mistral-nemo-12b.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3520c2b6da0877db057c4d0dda1987579d5b7b2b92819c3de4e14ec8dbe166
3
+ size 4791047360
mahou-1.5-mistral-nemo-12b.bf16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:541b7b748ddd409892649021ded21bddda598fb7ad0fa11ebe4b722b7084187d
3
+ size 24504276160