mradermacher commited on
Commit
8b3634a
1 Parent(s): 5c62578

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +66 -0
README.md CHANGED
@@ -1,5 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  weighted/imatrix quants of https://huggingface.co/Sao10K/Skadi-Mixtral-v1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: Sao10K/Skadi-Mixtral-v1
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: cc-by-nc-4.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - merge
10
+ ---
11
+ ## About
12
+
13
  <!-- ### quantize_version: 1 -->
14
  <!-- ### output_tensor_quantised: 1 -->
15
  <!-- ### convert_type: -->
16
  <!-- ### vocab_type: -->
17
  weighted/imatrix quants of https://huggingface.co/Sao10K/Skadi-Mixtral-v1
18
+
19
+
20
+ <!-- provided-files -->
21
+ static quants are available at https://huggingface.co/mradermacher/Skadi-Mixtral-v1-GGUF
22
+ ## Usage
23
+
24
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
25
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
26
+ more details, including on how to concatenate multi-part files.
27
+
28
+ ## Provided Quants
29
+
30
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
31
+
32
+ | Link | Type | Size/GB | Notes |
33
+ |:-----|:-----|--------:|:------|
34
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 9.9 | for the desperate |
35
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 10.9 | for the desperate |
36
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
41
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 20.5 | beats Q3_K* |
44
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 21.5 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
48
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.2 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_0.gguf) | i1-Q4_0 | 26.7 | fast, low quality |
50
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.3 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.3 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Skadi-Mixtral-v1-i1-GGUF/resolve/main/Skadi-Mixtral-v1.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | practically like static Q6_K |
55
+
56
+
57
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
58
+ types (lower is better):
59
+
60
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
61
+
62
+ And here are Artefact2's thoughts on the matter:
63
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
64
+
65
+ ## Thanks
66
+
67
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
68
+ me use its servers and providing upgrades to my workstation to enable
69
+ this work in my free time.
70
+
71
+ <!-- end -->