Hugging Face's logo

Casual-Autopsy
/
RP-Spectrum-24B

Text Generation
Transformers
Safetensors
mistral
mergekit
Merge
rp
roleplay
role-play
DELLA
conversational
text-generation-inference
Model card Files
xet
 Community
3
Casual-Autopsy commited on
Commit
33035eb
·
verified ·
1 Parent(s): 43a1b0e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -21
README.md CHANGED
@@ -1,14 +1,22 @@
1
  ---
2
- base_model: []
 
 
 
 
 
 
 
3
  library_name: transformers
4
  tags:
5
  - mergekit
6
  - merge
7
-
8
  ---
9
- # Untitled Model (1)
 
 
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
@@ -18,12 +26,12 @@ This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge
18
  ### Models Merged
19
 
20
  The following models were included in the merge:
21
- * /home/casauto/ML/Text/Models/HFs/MS3.2-24B-Magnum-Diamond
22
- * /home/casauto/ML/Text/Models/HFs/Dark-Nexus-24B-v2.0
23
- * /home/casauto/ML/Text/Models/HFs/Cydonia-24B-v4
24
- * /home/casauto/ML/Text/Models/HFs/MS3.2-PaintedFantasy-v3-24B
25
- * /home/casauto/ML/Text/Models/HFs/M3.2-24B-Loki-V1.3
26
- * /home/casauto/ML/Text/Models/HFs/Codex-24B-Small-3.2
27
 
28
  ### Configuration
29
 
@@ -31,46 +39,49 @@ The following YAML configuration was used to produce this model:
31
 
32
  ```yaml
33
  models:
34
- - model: /home/casauto/ML/Text/Models/HFs/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
35
- - model: /home/casauto/ML/Text/Models/HFs/MS3.2-PaintedFantasy-v3-24B
 
36
  parameters:
37
  weight: 0.3
38
  density: 1.0
39
  epsilon: 0.0
40
- - model: /home/casauto/ML/Text/Models/HFs/Cydonia-24B-v4
41
  parameters:
42
  weight: 0.3
43
  density: 0.4
44
  epsilon: 0.25
45
- - model: /home/casauto/ML/Text/Models/HFs/M3.2-24B-Loki-V1.3
46
  parameters:
47
  weight: 0.3
48
  density: 0.4
49
  epsilon: 0.25
50
- - model: /home/casauto/ML/Text/Models/HFs/Codex-24B-Small-3.2
51
  parameters:
52
  weight: 0.3
53
  density: 0.4
54
  epsilon: 0.25
55
- - model: /home/casauto/ML/Text/Models/HFs/Dark-Nexus-24B-v2.0
56
  parameters:
57
  weight: 0.3
58
  density: 0.4
59
  epsilon: 0.25
60
- - model: /home/casauto/ML/Text/Models/HFs/MS3.2-24B-Magnum-Diamond
61
  parameters:
62
  weight: 0.3
63
  density: 0.4
64
  epsilon: 0.25
 
 
65
  merge_method: della
66
  parameters:
67
  lambda: 0.9
68
  normalize: true
69
  int8_mask: false
70
- base_model: /home/casauto/ML/Text/Models/HFs/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
71
  dtype: float32
72
  out_dtype: bfloat16
73
- tokenizer:
74
- source: /home/casauto/ML/Text/Models/HFs/MS3.2-PaintedFantasy-v3-24B
75
 
76
- ```
 
 
 
1
  ---
2
+ base_model:
3
+ - TheDrummer/Cydonia-24B-v4
4
+ - ReadyArt/Dark-Nexus-24B-v2.0
5
+ - Doctor-Shotgun/MS3.2-24B-Magnum-Diamond
6
+ - zerofata/MS3.2-PaintedFantasy-v3-24B
7
+ - CrucibleLab/M3.2-24B-Loki-V1.3
8
+ - Gryphe/Codex-24B-Small-3.2
9
+ - mistralai/Mistral-Small-3.2-24B-Instruct-2506
10
  library_name: transformers
11
  tags:
12
  - mergekit
13
  - merge
 
14
  ---
15
+ # RP-Spectrum-24B
16
+
17
+ <img src="https://huggingface.co/Casual-Autopsy/RP-Spectrum-24B/resolve/main/RP-Spectrum.png">
18
 
19
+ A merge of some of the best RP finetunes the community has to offer.
20
 
21
  ## Merge Details
22
  ### Merge Method
 
26
  ### Models Merged
27
 
28
  The following models were included in the merge:
29
+ * [mistralai/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506)
30
+ * [zerofata/MS3.2-PaintedFantasy-v3-24B](https://huggingface.co/zerofata/MS3.2-PaintedFantasy-v3-24B)
31
+ * [TheDrummer/Cydonia-24B-v4](https://huggingface.co/TheDrummer/Cydonia-24B-v4)
32
+ * [ReadyArt/Dark-Nexus-24B-v2.0](https://huggingface.co/ReadyArt/Dark-Nexus-24B-v2.0)
33
+ * [Gryphe/Codex-24B-Small-3.2](https://huggingface.co/Gryphe/Codex-24B-Small-3.2)
34
+ * [Doctor-Shotgun/MS3.2-24B-Magnum-Diamond](https://huggingface.co/Doctor-Shotgun/MS3.2-24B-Magnum-Diamond)
35
 
36
  ### Configuration
37
 
 
39
 
40
  ```yaml
41
  models:
42
+ - model: mistralai/Mistral-Small-3.2-24B-Instruct-2506
43
+
44
+ - model: zerofata/MS3.2-PaintedFantasy-v3-24B # Pink/Red
45
  parameters:
46
  weight: 0.3
47
  density: 1.0
48
  epsilon: 0.0
49
+ - model: TheDrummer/Cydonia-24B-v4 # Black
50
  parameters:
51
  weight: 0.3
52
  density: 0.4
53
  epsilon: 0.25
54
+ - model: CrucibleLab/M3.2-24B-Loki-V1.3 # Green
55
  parameters:
56
  weight: 0.3
57
  density: 0.4
58
  epsilon: 0.25
59
+ - model: Gryphe/Codex-24B-Small-3.2 # Blue (Yes, blue. Fuck you.)
60
  parameters:
61
  weight: 0.3
62
  density: 0.4
63
  epsilon: 0.25
64
+ - model: ReadyArt/Dark-Nexus-24B-v2.0 # Orange
65
  parameters:
66
  weight: 0.3
67
  density: 0.4
68
  epsilon: 0.25
69
+ - model: Doctor-Shotgun/MS3.2-24B-Magnum-Diamond # White
70
  parameters:
71
  weight: 0.3
72
  density: 0.4
73
  epsilon: 0.25
74
+
75
+ # Seed: 199803
76
  merge_method: della
77
  parameters:
78
  lambda: 0.9
79
  normalize: true
80
  int8_mask: false
81
+ base_model: mistralai/Mistral-Small-3.2-24B-Instruct-2506
82
  dtype: float32
83
  out_dtype: bfloat16
 
 
84
 
85
+ tokenizer:
86
+ source: zerofata/MS3.2-PaintedFantasy-v3-24B
87
+ ```