Hugging Face's logo

RichardErkhov
/
saishf_-_Aura-Uncensored-OAS-8B-L3-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
ef6be3f
·
verified ·
1 Parent(s): 57400fd

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +99 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ Aura-Uncensored-OAS-8B-L3 - GGUF
11
+ - Model creator: https://huggingface.co/saishf/
12
+ - Original model: https://huggingface.co/saishf/Aura-Uncensored-OAS-8B-L3/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Aura-Uncensored-OAS-8B-L3.Q2_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q2_K.gguf) | Q2_K | 2.96GB |
18
+ | [Aura-Uncensored-OAS-8B-L3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
19
+ | [Aura-Uncensored-OAS-8B-L3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.IQ3_S.gguf) | IQ3_S | 3.43GB |
20
+ | [Aura-Uncensored-OAS-8B-L3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
21
+ | [Aura-Uncensored-OAS-8B-L3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.IQ3_M.gguf) | IQ3_M | 3.52GB |
22
+ | [Aura-Uncensored-OAS-8B-L3.Q3_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q3_K.gguf) | Q3_K | 3.74GB |
23
+ | [Aura-Uncensored-OAS-8B-L3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
24
+ | [Aura-Uncensored-OAS-8B-L3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
25
+ | [Aura-Uncensored-OAS-8B-L3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
26
+ | [Aura-Uncensored-OAS-8B-L3.Q4_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q4_0.gguf) | Q4_0 | 4.34GB |
27
+ | [Aura-Uncensored-OAS-8B-L3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
28
+ | [Aura-Uncensored-OAS-8B-L3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
29
+ | [Aura-Uncensored-OAS-8B-L3.Q4_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q4_K.gguf) | Q4_K | 4.58GB |
30
+ | [Aura-Uncensored-OAS-8B-L3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
31
+ | [Aura-Uncensored-OAS-8B-L3.Q4_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q4_1.gguf) | Q4_1 | 4.78GB |
32
+ | [Aura-Uncensored-OAS-8B-L3.Q5_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q5_0.gguf) | Q5_0 | 5.21GB |
33
+ | [Aura-Uncensored-OAS-8B-L3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
34
+ | [Aura-Uncensored-OAS-8B-L3.Q5_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q5_K.gguf) | Q5_K | 5.34GB |
35
+ | [Aura-Uncensored-OAS-8B-L3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
36
+ | [Aura-Uncensored-OAS-8B-L3.Q5_1.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q5_1.gguf) | Q5_1 | 5.65GB |
37
+ | [Aura-Uncensored-OAS-8B-L3.Q6_K.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.Q6_K.gguf) | Q6_K | 6.14GB |
38
+ | [Aura-Uncensored-OAS-8B-L3.Q8_0.gguf](https://huggingface.co/RichardErkhov/saishf_-_Aura-Uncensored-OAS-8B-L3-gguf/blob/main/Aura-Uncensored-OAS-8B-L3.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
+ - Undi95/Llama3-Unholy-8B-OAS
48
+ - ResplendentAI/Theory_of_Mind_Llama3
49
+ - Undi95/Llama3-Unholy-8B-OAS
50
+ - ResplendentAI/Luna_Llama3
51
+ - Undi95/Llama3-Unholy-8B-OAS
52
+ - Undi95/Llama3-Unholy-8B-OAS
53
+ - ResplendentAI/Aura_Llama3
54
+ - Undi95/Llama3-Unholy-8B-OAS
55
+ - ResplendentAI/BlueMoon_Llama3
56
+ - Undi95/Llama3-Unholy-8B-OAS
57
+ - ResplendentAI/RP_Format_QuoteAsterisk_Llama3
58
+ library_name: transformers
59
+ tags:
60
+ - mergekit
61
+ - merge
62
+
63
+ ---
64
+ # merge
65
+
66
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
67
+
68
+ ## Merge Details
69
+ This is a rerun of [ResplendentAI/Aura_Uncensored_l3_8B](https://huggingface.co/ResplendentAI/Aura_Uncensored_l3_8B) using [Undi95/Llama3-Unholy-8B-OAS](https://huggingface.co/Undi95/Llama3-Unholy-8B-OAS) instead of [Undi95/Llama-3-Unholy-8B](https://huggingface.co/Undi95/Llama-3-Unholy-8B) in the hopes it will result in a less censored, uncensored aura.
70
+ ### Merge Method
71
+
72
+ This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Undi95/Llama3-Unholy-8B-OAS](https://huggingface.co/Undi95/Llama3-Unholy-8B-OAS) as a base.
73
+
74
+ ### Models Merged
75
+
76
+ The following models were included in the merge:
77
+ * [Undi95/Llama3-Unholy-8B-OAS](https://huggingface.co/Undi95/Llama3-Unholy-8B-OAS) + [ResplendentAI/Theory_of_Mind_Llama3](https://huggingface.co/ResplendentAI/Theory_of_Mind_Llama3)
78
+ * [Undi95/Llama3-Unholy-8B-OAS](https://huggingface.co/Undi95/Llama3-Unholy-8B-OAS) + [ResplendentAI/Luna_Llama3](https://huggingface.co/ResplendentAI/Luna_Llama3)
79
+ * [Undi95/Llama3-Unholy-8B-OAS](https://huggingface.co/Undi95/Llama3-Unholy-8B-OAS) + [ResplendentAI/Aura_Llama3](https://huggingface.co/ResplendentAI/Aura_Llama3)
80
+ * [Undi95/Llama3-Unholy-8B-OAS](https://huggingface.co/Undi95/Llama3-Unholy-8B-OAS) + [ResplendentAI/BlueMoon_Llama3](https://huggingface.co/ResplendentAI/BlueMoon_Llama3)
81
+ * [Undi95/Llama3-Unholy-8B-OAS](https://huggingface.co/Undi95/Llama3-Unholy-8B-OAS) + [ResplendentAI/RP_Format_QuoteAsterisk_Llama3](https://huggingface.co/ResplendentAI/RP_Format_QuoteAsterisk_Llama3)
82
+
83
+ ### Configuration
84
+
85
+ The following YAML configuration was used to produce this model:
86
+
87
+ ```yaml
88
+ models:
89
+ - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/Theory_of_Mind_Llama3
90
+ - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/Aura_Llama3
91
+ - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/Luna_Llama3
92
+ - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/BlueMoon_Llama3
93
+ - model: Undi95/Llama3-Unholy-8B-OAS+ResplendentAI/RP_Format_QuoteAsterisk_Llama3
94
+ merge_method: model_stock
95
+ base_model: Undi95/Llama3-Unholy-8B-OAS
96
+ dtype: float16
97
+ ```
98
+
99
+