mradermacher commited on
Commit
0fe81d8
·
verified ·
1 Parent(s): fbd0ec6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +101 -0
README.md CHANGED
@@ -1,6 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - creative
10
+ - creative writing
11
+ - fiction writing
12
+ - plot generation
13
+ - sub-plot generation
14
+ - fiction writing
15
+ - story generation
16
+ - scene continue
17
+ - storytelling
18
+ - fiction story
19
+ - science fiction
20
+ - romance
21
+ - all genres
22
+ - story
23
+ - writing
24
+ - vivid prosing
25
+ - vivid writing
26
+ - fiction
27
+ - roleplaying
28
+ - bfloat16
29
+ - swearing
30
+ - role play
31
+ - sillytavern
32
+ - backyard
33
+ - horror
34
+ - llama 3.1
35
+ - context 128k
36
+ - mergekit
37
+ - merge
38
+ - not-for-all-audiences
39
+ ---
40
+ ## About
41
+
42
  <!-- ### quantize_version: 2 -->
43
  <!-- ### output_tensor_quantised: 1 -->
44
  <!-- ### convert_type: hf -->
45
  <!-- ### vocab_type: -->
46
  <!-- ### tags: nicoboss -->
47
  weighted/imatrix quants of https://huggingface.co/DavidAU/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B
48
+
49
+ <!-- provided-files -->
50
+ static quants are available at https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-GGUF
51
+ ## Usage
52
+
53
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
54
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
55
+ more details, including on how to concatenate multi-part files.
56
+
57
+ ## Provided Quants
58
+
59
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
60
+
61
+ | Link | Type | Size/GB | Notes |
62
+ |:-----|:-----|--------:|:------|
63
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
64
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
65
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | |
66
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | |
67
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | |
68
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | |
69
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
70
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
71
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
72
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | |
73
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
74
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
75
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | |
76
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
77
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
78
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | |
79
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
80
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
81
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
82
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
83
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | |
84
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | |
85
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | |
86
+ | [GGUF](https://huggingface.co/mradermacher/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B-i1-GGUF/resolve/main/L3.1-Evil-Reasoning-Dark-Planet-Hermes-R1-Uncensored-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
87
+
88
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
89
+ types (lower is better):
90
+
91
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
92
+
93
+ And here are Artefact2's thoughts on the matter:
94
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
95
+
96
+ ## FAQ / Model Request
97
+
98
+ See https://huggingface.co/mradermacher/model_requests for some answers to
99
+ questions you might have and/or if you want some other model quantized.
100
+
101
+ ## Thanks
102
+
103
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
104
+ me use its servers and providing upgrades to my workstation to enable
105
+ 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.
106
+
107
+ <!-- end -->