Hugging Face's logo

RichardErkhov
/
saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf

GGUF
Inference Endpoints
Model card Files Community
RichardErkhov commited on
Commit
fdd6ab0
•
1 Parent(s): d014f79

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +88 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ SOVL-Mega-Mash-V2-L3-8B - GGUF
11
+ - Model creator: https://huggingface.co/saishf/
12
+ - Original model: https://huggingface.co/saishf/SOVL-Mega-Mash-V2-L3-8B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [SOVL-Mega-Mash-V2-L3-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [SOVL-Mega-Mash-V2-L3-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [SOVL-Mega-Mash-V2-L3-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [SOVL-Mega-Mash-V2-L3-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
21
+ | [SOVL-Mega-Mash-V2-L3-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [SOVL-Mega-Mash-V2-L3-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [SOVL-Mega-Mash-V2-L3-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [SOVL-Mega-Mash-V2-L3-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [SOVL-Mega-Mash-V2-L3-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [SOVL-Mega-Mash-V2-L3-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [SOVL-Mega-Mash-V2-L3-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [SOVL-Mega-Mash-V2-L3-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [SOVL-Mega-Mash-V2-L3-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [SOVL-Mega-Mash-V2-L3-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [SOVL-Mega-Mash-V2-L3-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [SOVL-Mega-Mash-V2-L3-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [SOVL-Mega-Mash-V2-L3-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [SOVL-Mega-Mash-V2-L3-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q5_K.gguf) | Q5_K | 4.85GB |
35
+ | [SOVL-Mega-Mash-V2-L3-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [SOVL-Mega-Mash-V2-L3-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [SOVL-Mega-Mash-V2-L3-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [SOVL-Mega-Mash-V2-L3-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_SOVL-Mega-Mash-V2-L3-8B-gguf/blob/main/SOVL-Mega-Mash-V2-L3-8B.Q8_0.gguf) | Q8_0 | 7.95GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: cc-by-nc-4.0
46
+ base_model:
47
+ - saishf/SOVLish-Maid-L3-8B
48
+ - saishf/Neural-SOVLish-Devil-8B-L3
49
+ - saishf/Merge-Mayhem-L3-V2
50
+ - saishf/Merge-Mayhem-L3-V2.1
51
+ library_name: transformers
52
+ tags:
53
+ - mergekit
54
+ - merge
55
+
56
+ ---
57
+ # merge
58
+
59
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
60
+
61
+ ## Merge Details
62
+ ### Merge Method
63
+
64
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [saishf/Neural-SOVLish-Devil-8B-L3](https://huggingface.co/saishf/Neural-SOVLish-Devil-8B-L3) as a base.
65
+
66
+ ### Models Merged
67
+
68
+ The following models were included in the merge:
69
+ * [saishf/SOVLish-Maid-L3-8B](https://huggingface.co/saishf/SOVLish-Maid-L3-8B)
70
+ * [saishf/Merge-Mayhem-L3-V2](https://huggingface.co/saishf/Merge-Mayhem-L3-V2)
71
+ * [saishf/Merge-Mayhem-L3-V2.1](https://huggingface.co/saishf/Merge-Mayhem-L3-V2.1)
72
+
73
+ ### Configuration
74
+
75
+ The following YAML configuration was used to produce this model:
76
+
77
+ ```yaml
78
+ models:
79
+ - model: saishf/Neural-SOVLish-Devil-8B-L3
80
+ - model: saishf/Merge-Mayhem-L3-V2
81
+ - model: saishf/Merge-Mayhem-L3-V2.1
82
+ - model: saishf/SOVLish-Maid-L3-8B
83
+ merge_method: model_stock
84
+ base_model: saishf/Neural-SOVLish-Devil-8B-L3
85
+ dtype: bfloat16
86
+ ```
87
+
88
+