mradermacher commited on
Commit
58784aa
·
verified ·
1 Parent(s): b5412f0

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md CHANGED
@@ -1,6 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/DavidAU/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored
3
+ language:
4
+ - en
5
+ - fr
6
+ - zh
7
+ - de
8
+ library_name: transformers
9
+ license: apache-2.0
10
+ quantized_by: mradermacher
11
+ tags:
12
+ - creative
13
+ - creative writing
14
+ - fiction writing
15
+ - plot generation
16
+ - sub-plot generation
17
+ - fiction writing
18
+ - story generation
19
+ - scene continue
20
+ - storytelling
21
+ - fiction story
22
+ - science fiction
23
+ - romance
24
+ - all genres
25
+ - story
26
+ - writing
27
+ - vivid prose
28
+ - vivid writing
29
+ - moe
30
+ - mixture of experts
31
+ - 64 experts
32
+ - 8 active experts
33
+ - fiction
34
+ - roleplaying
35
+ - bfloat16
36
+ - rp
37
+ - qwen3
38
+ - horror
39
+ - finetune
40
+ - thinking
41
+ - reasoning
42
+ - qwen3_moe
43
+ - merge
44
+ - uncensored
45
+ - abliterated
46
+ - not-for-all-audiences
47
+ ---
48
+ ## About
49
+
50
  <!-- ### quantize_version: 2 -->
51
  <!-- ### output_tensor_quantised: 1 -->
52
  <!-- ### convert_type: hf -->
53
  <!-- ### vocab_type: -->
54
  <!-- ### tags: nicoboss -->
55
  weighted/imatrix quants of https://huggingface.co/DavidAU/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored
56
+
57
+ <!-- provided-files -->
58
+ static quants are available at https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-GGUF
59
+ ## Usage
60
+
61
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
62
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
63
+ more details, including on how to concatenate multi-part files.
64
+
65
+ ## Provided Quants
66
+
67
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
68
+
69
+ | Link | Type | Size/GB | Notes |
70
+ |:-----|:-----|--------:|:------|
71
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-IQ2_M.gguf) | i1-IQ2_M | 7.5 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q2_K_S.gguf) | i1-Q2_K_S | 7.8 | very low quality |
73
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q2_K.gguf) | i1-Q2_K | 8.3 | IQ3_XXS probably better |
74
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 8.7 | lower quality |
75
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-IQ3_XS.gguf) | i1-IQ3_XS | 9.3 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.8 | IQ3_XS probably better |
77
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-IQ3_S.gguf) | i1-IQ3_S | 9.8 | beats Q3_K* |
78
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-IQ3_M.gguf) | i1-IQ3_M | 10.0 | |
79
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.8 | IQ3_S probably better |
80
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q3_K_L.gguf) | i1-Q3_K_L | 11.7 | IQ3_M probably better |
81
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.0 | |
82
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q4_0.gguf) | i1-Q4_0 | 12.7 | fast, low quality |
83
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 12.8 | optimal size/speed/quality |
84
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q4_K_M.gguf) | i1-Q4_K_M | 13.5 | fast, recommended |
85
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q4_1.gguf) | i1-Q4_1 | 14.0 | |
86
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q5_K_S.gguf) | i1-Q5_K_S | 15.4 | |
87
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q5_K_M.gguf) | i1-Q5_K_M | 15.8 | |
88
+ | [GGUF](https://huggingface.co/mradermacher/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored-i1-GGUF/resolve/main/Qwen3-22B-A3B-The-Harley-Quinn-PUDDIN-Abliterated-Uncensored.i1-Q6_K.gguf) | i1-Q6_K | 18.3 | practically like static Q6_K |
89
+
90
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
91
+ types (lower is better):
92
+
93
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
94
+
95
+ And here are Artefact2's thoughts on the matter:
96
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
97
+
98
+ ## FAQ / Model Request
99
+
100
+ See https://huggingface.co/mradermacher/model_requests for some answers to
101
+ questions you might have and/or if you want some other model quantized.
102
+
103
+ ## Thanks
104
+
105
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
106
+ me use its servers and providing upgrades to my workstation to enable
107
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
108
+
109
+ <!-- end -->