mradermacher commited on
Commit
000fc7e
·
verified ·
1 Parent(s): b62c716

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +56 -0
README.md CHANGED
@@ -1,3 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### convert_type: -->
2
  <!-- ### vocab_type: -->
3
  weighted/imatrix quants of https://huggingface.co/Undi95/Miqu-MS-70B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - migtissera/Tess-70B-v1.6
4
+ - 152334H/miqu-1-70b-sf
5
+ - NeverSleep/MiquMaid-v2-70B
6
+ - sophosympatheia/Midnight-Miqu-70B-v1.0
7
+ exported_from: Undi95/Miqu-MS-70B
8
+ language:
9
+ - en
10
+ library_name: transformers
11
+ license: cc-by-nc-4.0
12
+ quantized_by: mradermacher
13
+ tags:
14
+ - mergekit
15
+ - merge
16
+ ---
17
+ ## About
18
+
19
  <!-- ### convert_type: -->
20
  <!-- ### vocab_type: -->
21
  weighted/imatrix quants of https://huggingface.co/Undi95/Miqu-MS-70B
22
+
23
+
24
+ <!-- provided-files -->
25
+ static quants are available at https://huggingface.co/mradermacher/Miqu-MS-70B-GGUF
26
+ ## Usage
27
+
28
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
29
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
30
+ more details, including on how to concatenate multi-part files.
31
+
32
+ ## Provided Quants
33
+
34
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
35
+
36
+ | Link | Type | Size/GB | Notes |
37
+ |:-----|:-----|--------:|:------|
38
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-MS-70B-i1-GGUF/resolve/main/Miqu-MS-70B.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
39
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-MS-70B-i1-GGUF/resolve/main/Miqu-MS-70B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 27.0 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-MS-70B-i1-GGUF/resolve/main/Miqu-MS-70B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
41
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-MS-70B-i1-GGUF/resolve/main/Miqu-MS-70B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-MS-70B-i1-GGUF/resolve/main/Miqu-MS-70B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
43
+
44
+
45
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
46
+ types (lower is better):
47
+
48
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
49
+
50
+ And here are Artefact2's thoughts on the matter:
51
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
52
+
53
+ ## Thanks
54
+
55
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
56
+ me use its servers and providing upgrades to my workstation to enable
57
+ this work in my free time.
58
+
59
+ <!-- end -->