Hugging Face's logo

mradermacher
/
DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF

Transformers
GGUF
PyTorch
roleplay
llama3
sillytavern
idol
facebook
meta
llama
llama-3
Inference Endpoints
imatrix
conversational
Model card Files Community
1
mradermacher commited on
Commit
587c075
·
verified ·
1 Parent(s): 023b4c9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +102 -0
README.md CHANGED
@@ -1,6 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: nicoboss -->
6
  weighted/imatrix quants of https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
3
+ extra_gated_fields:
4
+ Affiliation: text
5
+ Country: country
6
+ Date of birth: date_picker
7
+ First Name: text
8
+ Job title:
9
+ options:
10
+ - Student
11
+ - Research Graduate
12
+ - AI researcher
13
+ - AI developer/engineer
14
+ - Reporter
15
+ - Other
16
+ type: select
17
+ Last Name: text
18
+ language:
19
+ - en
20
+ - de
21
+ - fr
22
+ - it
23
+ - pt
24
+ - hi
25
+ - es
26
+ - th
27
+ - zh
28
+ - ko
29
+ - ja
30
+ library_name: transformers
31
+ license: llama3.1
32
+ quantized_by: mradermacher
33
+ tags:
34
+ - roleplay
35
+ - llama3
36
+ - sillytavern
37
+ - idol
38
+ - facebook
39
+ - meta
40
+ - pytorch
41
+ - llama
42
+ - llama-3
43
+ ---
44
+ ## About
45
+
46
  <!-- ### quantize_version: 2 -->
47
  <!-- ### output_tensor_quantised: 1 -->
48
  <!-- ### convert_type: hf -->
49
  <!-- ### vocab_type: -->
50
  <!-- ### tags: nicoboss -->
51
  weighted/imatrix quants of https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
52
+
53
+ <!-- provided-files -->
54
+ static quants are available at https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-GGUF
55
+ ## Usage
56
+
57
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
58
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
59
+ more details, including on how to concatenate multi-part files.
60
+
61
+ ## Provided Quants
62
+
63
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
64
+
65
+ | Link | Type | Size/GB | Notes |
66
+ |:-----|:-----|--------:|:------|
67
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
68
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
69
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
74
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
75
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
77
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
78
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
79
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
80
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
81
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
82
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
83
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
84
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
85
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
86
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
87
+ | [GGUF](https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored-i1-GGUF/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
88
+
89
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
90
+ types (lower is better):
91
+
92
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
93
+
94
+ And here are Artefact2's thoughts on the matter:
95
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
96
+
97
+ ## FAQ / Model Request
98
+
99
+ See https://huggingface.co/mradermacher/model_requests for some answers to
100
+ questions you might have and/or if you want some other model quantized.
101
+
102
+ ## Thanks
103
+
104
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
105
+ me use its servers and providing upgrades to my workstation to enable
106
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.
107
+
108
+ <!-- end -->