mradermacher commited on
Commit
ab0875e
1 Parent(s): 8e9a2f6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +59 -0
README.md CHANGED
@@ -1 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/ChuckMcSneed/Premerge-EX-EX-123B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: ChuckMcSneed/Premerge-EX-EX-123B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: llama2
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - merge
10
+ - mergekit
11
+ ---
12
+ ## About
13
+
14
  static quants of https://huggingface.co/ChuckMcSneed/Premerge-EX-EX-123B
15
+
16
+
17
+ <!-- provided-files -->
18
+ 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.
19
+ ## Usage
20
+
21
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
22
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
23
+ more details, including on how to concatenate multi-part files.
24
+
25
+ ## Provided Quants
26
+
27
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
28
+
29
+ | Link | Type | Size/GB | Notes |
30
+ |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q2_K.gguf) | Q2_K | 45.8 | |
32
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.IQ3_XS.gguf.part2of2) | IQ3_XS | 51.0 | |
33
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q3_K_S.gguf.part2of2) | Q3_K_S | 53.7 | |
34
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.IQ3_S.gguf.part2of2) | IQ3_S | 53.9 | beats Q3_K* |
35
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q3_K_M.gguf.part2of2) | Q3_K_M | 59.9 | lower quality |
36
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q3_K_L.gguf.part2of2) | Q3_K_L | 65.2 | |
37
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q4_0.gguf.part2of2) | Q4_0 | 70.1 | |
38
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q4_K_S.gguf.part2of2) | Q4_K_S | 70.6 | fast, recommended |
39
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q4_K_M.gguf.part2of2) | Q4_K_M | 74.6 | fast, recommended |
40
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q5_K_S.gguf.part2of2) | Q5_K_S | 85.5 | |
41
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q5_K_M.gguf.part2of2) | Q5_K_M | 87.8 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q6_K.gguf.part3of3) | Q6_K | 101.9 | very good quality |
43
+ | [PART 1](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Premerge-EX-EX-123B-GGUF/resolve/main/Premerge-EX-EX-123B.Q8_0.gguf.part3of3) | Q8_0 | 131.8 | fast, best quality |
44
+
45
+
46
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
47
+ types (lower is better):
48
+
49
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
50
+
51
+ And here are Artefact2's thoughts on the matter:
52
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
53
+
54
+ ## Thanks
55
+
56
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
57
+ me use its servers and providing upgrades to my workstation to enable
58
+ this work in my free time.
59
+
60
+ <!-- end -->