mradermacher commited on
Commit
6de13d4
1 Parent(s): 5ebe5f6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +56 -0
README.md CHANGED
@@ -1,6 +1,62 @@
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/migtissera/Tess-3-Mixtral-8x22B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: migtissera/Tess-3-Mixtral-8x22B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ quantized_by: mradermacher
8
+ ---
9
+ ## About
10
+
11
  <!-- ### quantize_version: 2 -->
12
  <!-- ### output_tensor_quantised: 1 -->
13
  <!-- ### convert_type: hf -->
14
  <!-- ### vocab_type: -->
15
  <!-- ### tags: -->
16
  static quants of https://huggingface.co/migtissera/Tess-3-Mixtral-8x22B
17
+
18
+ <!-- provided-files -->
19
+ weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
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
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q2_K.gguf.part2of2) | Q2_K | 52.2 | |
33
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q3_K_S.gguf.part2of2) | Q3_K_S | 61.6 | |
34
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q3_K_M.gguf.part2of2) | Q3_K_M | 67.9 | lower quality |
35
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q3_K_L.gguf.part2of2) | Q3_K_L | 72.7 | |
36
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.IQ4_XS.gguf.part2of2) | IQ4_XS | 76.5 | |
37
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q4_K_S.gguf.part2of2) | Q4_K_S | 80.6 | fast, recommended |
38
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q4_K_M.gguf.part2of2) | Q4_K_M | 85.7 | fast, recommended |
39
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q5_K_S.gguf.part2of2) | Q5_K_S | 97.1 | |
40
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q6_K.gguf.part3of3) | Q6_K | 115.6 | very good quality |
41
+ | [PART 1](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q8_0.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q8_0.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q8_0.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Tess-3-Mixtral-8x22B-GGUF/resolve/main/Tess-3-Mixtral-8x22B.Q8_0.gguf.part4of4) | Q8_0 | 149.5 | fast, best quality |
42
+
43
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
44
+ types (lower is better):
45
+
46
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
47
+
48
+ And here are Artefact2's thoughts on the matter:
49
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
50
+
51
+ ## FAQ / Model Request
52
+
53
+ See https://huggingface.co/mradermacher/model_requests for some answers to
54
+ questions you might have and/or if you want some other model quantized.
55
+
56
+ ## Thanks
57
+
58
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
59
+ me use its servers and providing upgrades to my workstation to enable
60
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
61
+
62
+ <!-- end -->