mradermacher commited on
Commit
2d66149
1 Parent(s): 439765b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +50 -0
README.md CHANGED
@@ -1 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  weighted/imatrix quants of https://huggingface.co/Netrve/Miqu-PlayMaid-2x70B-v0.1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: Netrve/Miqu-PlayMaid-2x70B-v0.1
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: cc-by-nc-4.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - not-for-all-audiences
10
+ - nsfw
11
+ ---
12
+ ## About
13
+
14
  weighted/imatrix quants of https://huggingface.co/Netrve/Miqu-PlayMaid-2x70B-v0.1
15
+
16
+
17
+ <!-- provided-files -->
18
+ static quants are available at https://huggingface.co/mradermacher/Miqu-PlayMaid-2x70B-v0.1-GGUF
19
+ ## Usage
20
+
21
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
22
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
23
+ more details, including on how to concatenate multi-part files.
24
+
25
+ ## Provided Quants
26
+
27
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
28
+
29
+ | Link | Type | Size/GB | Notes |
30
+ |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-PlayMaid-2x70B-v0.1-i1-GGUF/resolve/main/Miqu-PlayMaid-2x70B-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 46.3 | IQ3_XXS probably better |
32
+ | [PART 1](https://huggingface.co/mradermacher/Miqu-PlayMaid-2x70B-v0.1-i1-GGUF/resolve/main/Miqu-PlayMaid-2x70B-v0.1.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Miqu-PlayMaid-2x70B-v0.1-i1-GGUF/resolve/main/Miqu-PlayMaid-2x70B-v0.1.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 60.6 | IQ3_S probably better |
33
+ | [PART 1](https://huggingface.co/mradermacher/Miqu-PlayMaid-2x70B-v0.1-i1-GGUF/resolve/main/Miqu-PlayMaid-2x70B-v0.1.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Miqu-PlayMaid-2x70B-v0.1-i1-GGUF/resolve/main/Miqu-PlayMaid-2x70B-v0.1.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 71.7 | optimal size/speed/quality |
34
+ | [PART 1](https://huggingface.co/mradermacher/Miqu-PlayMaid-2x70B-v0.1-i1-GGUF/resolve/main/Miqu-PlayMaid-2x70B-v0.1.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Miqu-PlayMaid-2x70B-v0.1-i1-GGUF/resolve/main/Miqu-PlayMaid-2x70B-v0.1.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 76.0 | fast, recommended |
35
+
36
+
37
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
38
+ types (lower is better):
39
+
40
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
41
+
42
+ And here are Artefact2's thoughts on the matter:
43
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
44
+
45
+ ## Thanks
46
+
47
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
48
+ me use its servers and providing upgrades to my workstation to enable
49
+ this work in my free time.
50
+
51
+ <!-- end -->