mradermacher commited on
Commit
37dc5a4
·
verified ·
1 Parent(s): f88e483

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md CHANGED
@@ -1 +1,66 @@
 
 
 
 
 
 
 
 
 
 
1
  weighted/imatrix quants of https://huggingface.co/ajibawa-2023/Uncensored-Jordan-33B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: ajibawa-2023/Uncensored-Jordan-33B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: cc-by-nc-nd-4.0
7
+ quantized_by: mradermacher
8
+ ---
9
+ ## About
10
+
11
  weighted/imatrix quants of https://huggingface.co/ajibawa-2023/Uncensored-Jordan-33B
12
+
13
+
14
+ <!-- provided-files -->
15
+ static quants are available at https://huggingface.co/mradermacher/Uncensored-Jordan-33B-GGUF
16
+ ## Usage
17
+
18
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
19
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
20
+ more details, including on how to concatenate multi-part files.
21
+
22
+ ## Provided Quants
23
+
24
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
25
+
26
+ | Link | Type | Size/GB | Notes |
27
+ |:-----|:-----|--------:|:------|
28
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.5 | for the desperate |
29
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.1 | for the desperate |
30
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
31
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.8 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.6 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
35
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.7 | lower quality |
36
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.7 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.4 | beats Q3_K* |
38
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.4 | IQ3_XS probably better |
39
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ3_M.gguf) | i1-IQ3_M | 15.2 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.1 | IQ3_S probably better |
41
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.6 | IQ3_M probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 18.7 | slightly worse than Q4_K_S |
44
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.8 | optimal size/speed/quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Uncensored-Jordan-33B-i1-GGUF/resolve/main/Uncensored-Jordan-33B.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
50
+
51
+
52
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
53
+ types (lower is better):
54
+
55
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
56
+
57
+ And here are Artefact2's thoughts on the matter:
58
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
59
+
60
+ ## Thanks
61
+
62
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
63
+ me use its servers and providing upgrades to my workstation to enable
64
+ this work in my free time.
65
+
66
+ <!-- end -->