Hugging Face's logo

mradermacher
/
L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF

Transformers
GGUF
English
text-generation-inference
llama
Uncensored
Role-Play
RP
ERP
Erotic
Grim-Dark
Horror
MOE
Mixture-of-Experts
4x8
4x8b
Llama-3.1
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
e7209d6
·
verified ·
1 Parent(s): a4a64ec

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +87 -0
README.md CHANGED
@@ -1,6 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/Dunjeon/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Dunjeon/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ model_name: The BlackTower 4x8b
8
+ model_type: Mixture of Experts (MoE)
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - text-generation-inference
12
+ - transformers
13
+ - llama
14
+ - Uncensored
15
+ - Role-Play
16
+ - RP
17
+ - ERP
18
+ - Erotic
19
+ - Grim-Dark
20
+ - Horror
21
+ - MOE
22
+ - Mixture-of-Experts
23
+ - 4x8
24
+ - 4x8b
25
+ - Llama-3.1
26
+ ---
27
+ ## About
28
+
29
  <!-- ### quantize_version: 2 -->
30
  <!-- ### output_tensor_quantised: 1 -->
31
  <!-- ### convert_type: hf -->
32
  <!-- ### vocab_type: -->
33
  <!-- ### tags: nicoboss -->
34
  weighted/imatrix quants of https://huggingface.co/Dunjeon/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored
35
+
36
+ <!-- provided-files -->
37
+ static quants are available at https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-GGUF
38
+ ## Usage
39
+
40
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
41
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
42
+ more details, including on how to concatenate multi-part files.
43
+
44
+ ## Provided Quants
45
+
46
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
47
+
48
+ | Link | Type | Size/GB | Notes |
49
+ |:-----|:-----|--------:|:------|
50
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ1_S.gguf) | i1-IQ1_S | 5.5 | for the desperate |
51
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ1_M.gguf) | i1-IQ1_M | 6.0 | mostly desperate |
52
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.9 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.6 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ2_S.gguf) | i1-IQ2_S | 7.8 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ2_M.gguf) | i1-IQ2_M | 8.5 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.8 | very low quality |
57
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q2_K.gguf) | i1-Q2_K | 9.4 | IQ3_XXS probably better |
58
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.9 | lower quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.5 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q3_K_S.gguf) | i1-Q3_K_S | 11.0 | IQ3_XS probably better |
61
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ3_S.gguf) | i1-IQ3_S | 11.1 | beats Q3_K* |
62
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ3_M.gguf) | i1-IQ3_M | 11.2 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q3_K_M.gguf) | i1-Q3_K_M | 12.2 | IQ3_S probably better |
64
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.1 | IQ3_M probably better |
65
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.5 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q4_0.gguf) | i1-Q4_0 | 14.3 | fast, low quality |
67
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.4 | optimal size/speed/quality |
68
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.3 | fast, recommended |
69
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q4_1.gguf) | i1-Q4_1 | 15.8 | |
70
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q5_K_S.gguf) | i1-Q5_K_S | 17.3 | |
71
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.8 | |
72
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored-i1-GGUF/resolve/main/L3.1-4x8b_BlackTower_RP-V1.1-Uncensored.i1-Q6_K.gguf) | i1-Q6_K | 20.6 | practically like static Q6_K |
73
+
74
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
75
+ types (lower is better):
76
+
77
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
78
+
79
+ And here are Artefact2's thoughts on the matter:
80
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
81
+
82
+ ## FAQ / Model Request
83
+
84
+ See https://huggingface.co/mradermacher/model_requests for some answers to
85
+ questions you might have and/or if you want some other model quantized.
86
+
87
+ ## Thanks
88
+
89
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
90
+ me use its servers and providing upgrades to my workstation to enable
91
+ 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.
92
+
93
+ <!-- end -->