mradermacher commited on
Commit
9f10ab4
1 Parent(s): 6b31c0b

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +49 -0
README.md CHANGED
@@ -1 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/MarsupialAI/Yeet_51b_200k
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: MarsupialAI/Yeet_51b_200k
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: other
7
+ license_name: yi-other
8
+ quantized_by: mradermacher
9
+ ---
10
+ ## About
11
+
12
  static quants of https://huggingface.co/MarsupialAI/Yeet_51b_200k
13
+
14
+
15
+ <!-- provided-files -->
16
+ 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.
17
+ ## Usage
18
+
19
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
20
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
21
+ more details, including on how to concatenate multi-part files.
22
+
23
+ ## Provided Quants
24
+
25
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
26
+
27
+ | Link | Type | Size/GB | Notes |
28
+ |:-----|:-----|--------:|:------|
29
+ | [GGUF](https://huggingface.co/mradermacher/Yeet_51b_200k-GGUF/resolve/main/Yeet_51b_200k.Q2_K.gguf) | Q2_K | 19.6 | |
30
+ | [GGUF](https://huggingface.co/mradermacher/Yeet_51b_200k-GGUF/resolve/main/Yeet_51b_200k.IQ3_S.gguf) | IQ3_S | 22.9 | beats Q3_K* |
31
+ | [GGUF](https://huggingface.co/mradermacher/Yeet_51b_200k-GGUF/resolve/main/Yeet_51b_200k.Q3_K_M.gguf) | Q3_K_M | 25.3 | lower quality |
32
+ | [GGUF](https://huggingface.co/mradermacher/Yeet_51b_200k-GGUF/resolve/main/Yeet_51b_200k.Q4_K_S.gguf) | Q4_K_S | 29.7 | fast, recommended |
33
+ | [PART 1](https://huggingface.co/mradermacher/Yeet_51b_200k-GGUF/resolve/main/Yeet_51b_200k.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Yeet_51b_200k-GGUF/resolve/main/Yeet_51b_200k.Q8_0.gguf.part2of2) | Q8_0 | 54.9 | fast, best quality |
34
+
35
+
36
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
37
+ types (lower is better):
38
+
39
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
40
+
41
+ And here are Artefact2's thoughts on the matter:
42
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
43
+
44
+ ## Thanks
45
+
46
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
47
+ me use its servers and providing upgrades to my workstation to enable
48
+ this work in my free time.
49
+
50
+ <!-- end -->