mradermacher commited on
Commit
174d5e2
1 Parent(s): 655f427

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md CHANGED
@@ -1,6 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
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/FluffyKaeloky/Luminum-v0.1-123B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: FluffyKaeloky/Luminum-v0.1-123B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ tags:
8
+ - mergekit
9
+ - merge
10
+ ---
11
+ ## About
12
+
13
  <!-- ### quantize_version: 2 -->
14
  <!-- ### output_tensor_quantised: 1 -->
15
  <!-- ### convert_type: hf -->
16
  <!-- ### vocab_type: -->
17
  <!-- ### tags: -->
18
  static quants of https://huggingface.co/FluffyKaeloky/Luminum-v0.1-123B
19
+
20
+ <!-- provided-files -->
21
+ 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.
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/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q2_K.gguf) | Q2_K | 45.3 | |
35
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.IQ3_XS.gguf.part2of2) | IQ3_XS | 50.2 | |
36
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q3_K_S.gguf.part2of2) | Q3_K_S | 52.9 | |
37
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.IQ3_S.gguf.part2of2) | IQ3_S | 53.1 | beats Q3_K* |
38
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.IQ3_M.gguf.part2of2) | IQ3_M | 55.4 | |
39
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q3_K_M.gguf.part2of2) | Q3_K_M | 59.2 | lower quality |
40
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q3_K_L.gguf.part2of2) | Q3_K_L | 64.7 | |
41
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.IQ4_XS.gguf.part2of2) | IQ4_XS | 66.1 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q4_K_S.gguf.part2of2) | Q4_K_S | 69.7 | fast, recommended |
43
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q4_K_M.gguf.part2of2) | Q4_K_M | 73.3 | fast, recommended |
44
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q5_K_S.gguf.part2of2) | Q5_K_S | 84.5 | |
45
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q5_K_M.gguf.part2of2) | Q5_K_M | 86.6 | |
46
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q6_K.gguf.part3of3) | Q6_K | 100.7 | very good quality |
47
+ | [PART 1](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Luminum-v0.1-123B-GGUF/resolve/main/Luminum-v0.1-123B.Q8_0.gguf.part3of3) | Q8_0 | 130.4 | fast, best quality |
48
+
49
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
50
+ types (lower is better):
51
+
52
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
53
+
54
+ And here are Artefact2's thoughts on the matter:
55
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
56
+
57
+ ## FAQ / Model Request
58
+
59
+ See https://huggingface.co/mradermacher/model_requests for some answers to
60
+ questions you might have and/or if you want some other model quantized.
61
+
62
+ ## Thanks
63
+
64
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
65
+ me use its servers and providing upgrades to my workstation to enable
66
+ this work in my free time.
67
+
68
+ <!-- end -->