mradermacher commited on
Commit
0a79e5b
·
verified ·
1 Parent(s): 0aa619e

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/sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - mistralai/Mixtral-8x7B-Instruct-v0.1
4
+ exported_from: sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss-Instruct
5
+ language:
6
+ - en
7
+ library_name: transformers
8
+ quantized_by: mradermacher
9
+ tags:
10
+ - mergekit
11
+ - merge
12
+ ---
13
+ ## About
14
+
15
  weighted/imatrix quants of https://huggingface.co/sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss-Instruct
16
+
17
+
18
+ <!-- provided-files -->
19
+ static quants are available at https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-GGUF
20
+ ## Usage
21
+
22
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
23
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
24
+ more details, including on how to concatenate multi-part files.
25
+
26
+ ## Provided Quants
27
+
28
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
29
+
30
+ | Link | Type | Size/GB | Notes |
31
+ |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.8 | |
33
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.2 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 15.8 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 17.6 | IQ3_XXS probably better |
36
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.5 | lower quality |
37
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 20.7 | beats Q3_K* |
39
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.7 | IQ3_XS probably better |
40
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 21.7 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.8 | IQ3_S probably better |
42
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.4 | IQ3_M probably better |
43
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.3 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 26.8 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 27.0 | optimal size/speed/quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.7 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.5 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.5 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Air-Striker-Mixtral-8x7B-ZLoss-Instruct-i1-GGUF/resolve/main/Air-Striker-Mixtral-8x7B-ZLoss-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 38.6 | 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 -->