Hugging Face's logo

jeiku
/
Filet_3B_GGUF

GGUF
mergekit
Merge
Inference Endpoints
conversational
Model card Files Community
jeiku commited on
Commit
0320a43
•
1 Parent(s): d8c7244

Upload 8 files

Browse files
Files changed (9) hide show
  1. .gitattributes +7 -0
  2. Filet-Q2_K.gguf +3 -0
  3. Filet-Q3_K.gguf +3 -0
  4. Filet-Q4_K.gguf +3 -0
  5. Filet-Q4_K_S.gguf +3 -0
  6. Filet-Q5_K.gguf +3 -0
  7. Filet-Q6_K.gguf +3 -0
  8. Filet-f16.gguf +3 -0
  9. README.md +112 -0
.gitattributes CHANGED
@@ -33,3 +33,10 @@ 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
+ Filet-f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Filet-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Filet-Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Filet-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Filet-Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Filet-Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Filet-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Filet-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b12486f97550a644afa72a0ebe998f6c29769a613108eece82ed267ec6aa0580
3
+ size 1083755840
Filet-Q3_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc0e560aa23240c341c4ba7479f464c8563ee82e78b3d797d38f26a1930f72f9
3
+ size 1391419200
Filet-Q4_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c151078681e77942155406db3795e47aa103e4b4fb5ac3080a1321f0e77ff5d6
3
+ size 1708595520
Filet-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36188bfff224c5f78d26f87503979515e92bbcefac9534d9f93040c152a61938
3
+ size 1620695360
Filet-Q5_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c6b0fb9e387b9122c525bfc1040cb0566c01ffac199298f3808a22237e007f
3
+ size 1993390400
Filet-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97e4413fc0a6627e2d8ddb546553c481b512b4af426d9748c41865848b6c907
3
+ size 2295984960
Filet-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7af5379e3f4d259456fe9973b0d4d5edbf18bdaf61333cfce0c31e3486e9bf3
3
+ size 5593341696
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - jeiku/Rosa_v1_3B
4
+ - jeiku/Gnosis_256_StableLM
5
+ - jeiku/Rosa_v1_3B
6
+ - jeiku/Toxic_DPO_StableLM
7
+ - jeiku/Rosa_v1_3B
8
+ - jeiku/PIPPA_128_StableLM
9
+ - jeiku/Rosa_v1_3B
10
+ - jeiku/Theory_of_Mind_RP_128_StableLM
11
+ - jeiku/Rosa_v1_3B
12
+ - jeiku/Alpaca_128_StableLM
13
+ - jeiku/Rosa_v1_3B
14
+ - jeiku/RPGPT_StableLM
15
+ - jeiku/Rosa_v1_3B
16
+ - jeiku/Bluemoon_cleaned_StableLM
17
+ - jeiku/Rosa_v1_3B
18
+ - jeiku/Everything_v3_128_StableLM
19
+ - jeiku/Rosa_v1_3B
20
+ - jeiku/Theory_of_Mind_128_StableLM
21
+ - jeiku/Rosa_v1_3B
22
+ - jeiku/Humiliation_StableLM
23
+ - jeiku/Rosa_v1_3B
24
+ - jeiku/Rosa_v1_3B
25
+ - jeiku/LimaRP_StableLM
26
+ - jeiku/Rosa_v1_3B
27
+ - jeiku/Futa_Erotica_StableLM
28
+ - jeiku/Rosa_v1_3B
29
+ - jeiku/No_Robots_Alpaca_StableLM
30
+ tags:
31
+ - mergekit
32
+ - merge
33
+
34
+ ---
35
+ # futamix
36
+
37
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
38
+
39
+ ## Merge Details
40
+ ### Merge Method
41
+
42
+ This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) as a base.
43
+
44
+ ### Models Merged
45
+
46
+ The following models were included in the merge:
47
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Gnosis_256_StableLM](https://huggingface.co/jeiku/Gnosis_256_StableLM)
48
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Toxic_DPO_StableLM](https://huggingface.co/jeiku/Toxic_DPO_StableLM)
49
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/PIPPA_128_StableLM](https://huggingface.co/jeiku/PIPPA_128_StableLM)
50
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Theory_of_Mind_RP_128_StableLM](https://huggingface.co/jeiku/Theory_of_Mind_RP_128_StableLM)
51
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Alpaca_128_StableLM](https://huggingface.co/jeiku/Alpaca_128_StableLM)
52
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/RPGPT_StableLM](https://huggingface.co/jeiku/RPGPT_StableLM)
53
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Bluemoon_cleaned_StableLM](https://huggingface.co/jeiku/Bluemoon_cleaned_StableLM)
54
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Everything_v3_128_StableLM](https://huggingface.co/jeiku/Everything_v3_128_StableLM)
55
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Theory_of_Mind_128_StableLM](https://huggingface.co/jeiku/Theory_of_Mind_128_StableLM)
56
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Humiliation_StableLM](https://huggingface.co/jeiku/Humiliation_StableLM)
57
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/LimaRP_StableLM](https://huggingface.co/jeiku/LimaRP_StableLM)
58
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/Futa_Erotica_StableLM](https://huggingface.co/jeiku/Futa_Erotica_StableLM)
59
+ * [jeiku/Rosa_v1_3B](https://huggingface.co/jeiku/Rosa_v1_3B) + [jeiku/No_Robots_Alpaca_StableLM](https://huggingface.co/jeiku/No_Robots_Alpaca_StableLM)
60
+
61
+ ### Configuration
62
+
63
+ The following YAML configuration was used to produce this model:
64
+
65
+ ```yaml
66
+ merge_method: task_arithmetic
67
+ base_model: jeiku/Rosa_v1_3B
68
+ parameters:
69
+ normalize: true
70
+ models:
71
+ - model: jeiku/Rosa_v1_3B+jeiku/No_Robots_Alpaca_StableLM
72
+ parameters:
73
+ weight: 0.5
74
+ - model: jeiku/Rosa_v1_3B+jeiku/Toxic_DPO_StableLM
75
+ parameters:
76
+ weight: 0.5
77
+ - model: jeiku/Rosa_v1_3B+jeiku/Alpaca_128_StableLM
78
+ parameters:
79
+ weight: 0.4
80
+ - model: jeiku/Rosa_v1_3B+jeiku/Everything_v3_128_StableLM
81
+ parameters:
82
+ weight: 0.4
83
+ - model: jeiku/Rosa_v1_3B+jeiku/Futa_Erotica_StableLM
84
+ parameters:
85
+ weight: 1
86
+ - model: jeiku/Rosa_v1_3B+jeiku/Gnosis_256_StableLM
87
+ parameters:
88
+ weight: 1
89
+ - model: jeiku/Rosa_v1_3B+jeiku/Humiliation_StableLM
90
+ parameters:
91
+ weight: 1
92
+ - model: jeiku/Rosa_v1_3B+jeiku/Theory_of_Mind_128_StableLM
93
+ parameters:
94
+ weight: 0.8
95
+ - model: jeiku/Rosa_v1_3B+jeiku/PIPPA_128_StableLM
96
+ parameters:
97
+ weight: 0.4
98
+ - model: jeiku/Rosa_v1_3B+jeiku/LimaRP_StableLM
99
+ parameters:
100
+ weight: 0.7
101
+ - model: jeiku/Rosa_v1_3B+jeiku/Theory_of_Mind_RP_128_StableLM
102
+ parameters:
103
+ weight: 0.6
104
+ - model: jeiku/Rosa_v1_3B+jeiku/Bluemoon_cleaned_StableLM
105
+ parameters:
106
+ weight: 0.8
107
+ - model: jeiku/Rosa_v1_3B+jeiku/RPGPT_StableLM
108
+ parameters:
109
+ weight: 0.4
110
+ dtype: float16
111
+
112
+ ```