schnapper79 commited on
Commit
f6f38d1
1 Parent(s): 5bf79f3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -14
README.md CHANGED
@@ -1,26 +1,37 @@
1
  ---
 
 
 
2
  base_model: []
3
  library_name: transformers
4
  tags:
5
  - mergekit
6
- - merge
7
 
8
  ---
9
- # lumikabra_v0.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
 
11
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
 
13
  ## Merge Details
14
  ### Merge Method
15
 
16
- This model was merged using the della_linear merge method using /workspace/text-generation-webui/models/mistralai_Mistral-Large-Instruct-2407 as a base.
17
-
18
- ### Models Merged
19
 
20
- The following models were included in the merge:
21
- * /workspace/text-generation-webui/models/anthracite-org_magnum-v2-123b
22
- * /workspace/text-generation-webui/models/FluffyKaeloky_Luminum-v0.1-123B
23
- * /workspace/text-generation-webui/models/migtissera_Tess-3-Mistral-Large-2-123B
24
 
25
  ### Configuration
26
 
@@ -28,20 +39,20 @@ The following YAML configuration was used to produce this model:
28
 
29
  ```yaml
30
  models:
31
- - model: /workspace/text-generation-webui/models/anthracite-org_magnum-v2-123b
32
  parameters:
33
  weight: 0.24
34
  density: 0.5
35
- - model: /workspace/text-generation-webui/models/FluffyKaeloky_Luminum-v0.1-123B
36
  parameters:
37
  weight: 0.34
38
  density: 0.8
39
- - model: /workspace/text-generation-webui/models/migtissera_Tess-3-Mistral-Large-2-123B
40
  parameters:
41
  weight: 0.24
42
  density: 0.9
43
  merge_method: della_linear
44
- base_model: /workspace/text-generation-webui/models/mistralai_Mistral-Large-Instruct-2407
45
  parameters:
46
  epsilon: 0.05
47
  lambda: 1
 
1
  ---
2
+ license: other
3
+ license_name: mistral-ai-research-licence
4
+ license_link: https://mistral.ai/licenses/MRL-0.1.md
5
  base_model: []
6
  library_name: transformers
7
  tags:
8
  - mergekit
9
+ - lumikabra-123B
10
 
11
  ---
12
+ # lumikabra-123B v0.2
13
+
14
+
15
+ <div style="width: auto; margin-left: auto; margin-right: auto; margin-bottom: 3cm">
16
+ <img src="https://huggingface.co/schnapper79/lumikabra-123B_v0.1/resolve/main/lumikabra.png" alt="Lumikabra" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+
19
+ This is lumikabra. It's based on [Mistral-Large-Instruct-2407 ](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407), merged with Magnum-v2-123B, Luminum-v0.1-123B and Tess-3-Mistral-Large-2-123B.
20
+
21
+ I shamelessly took this idea from [FluffyKaeloky](https://huggingface.co/FluffyKaeloky/Luminum-v0.1-123B). Like him, i always had my troubles with each of the current large mistral based models.
22
+ Either it gets repetitive, shows too many GPTisms, is too horny or too unhorny. RP and storytelling is always a matter of taste, and i found myself swiping too often for new answers or even fixing them when I missed a little spice or cleverness.
23
+
24
+ Luminum was a great improvement, mixing a lot of desired traits, but I still missed some spice, another sauce.
25
+ So i took Luminum, added magnum again and also Tess for knowledge and structure.
26
+
27
+ This is a second version with another mixture of the same sauce. It is different than v0.1, not worse not better, just a little different. Again, I believe it is just a matter of taste, which answers one prefers and like the most.
28
 
 
29
 
30
  ## Merge Details
31
  ### Merge Method
32
 
33
+ This model was merged using [mergekit](https://github.com/cg123/mergekit) with the della_linear merge method using mistralai_Mistral-Large-Instruct-2407 as a base.
 
 
34
 
 
 
 
 
35
 
36
  ### Configuration
37
 
 
39
 
40
  ```yaml
41
  models:
42
+ - model: anthracite-org_magnum-v2-123b
43
  parameters:
44
  weight: 0.24
45
  density: 0.5
46
+ - model: FluffyKaeloky_Luminum-v0.1-123B
47
  parameters:
48
  weight: 0.34
49
  density: 0.8
50
+ - model: migtissera_Tess-3-Mistral-Large-2-123B
51
  parameters:
52
  weight: 0.24
53
  density: 0.9
54
  merge_method: della_linear
55
+ base_model: mistralai_Mistral-Large-Instruct-2407
56
  parameters:
57
  epsilon: 0.05
58
  lambda: 1