mradermacher commited on
Commit
995f586
1 Parent(s): 060bf94

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +48 -0
README.md CHANGED
@@ -1 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  weighted/imatrix quants of https://huggingface.co/MayaPH/GodziLLa-30B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: MayaPH/GodziLLa-30B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: cc-by-nc-4.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - merge
10
+ - mix
11
+ - cot
12
+ ---
13
+ ## About
14
+
15
  weighted/imatrix quants of https://huggingface.co/MayaPH/GodziLLa-30B
16
+
17
+
18
+ <!-- provided-files -->
19
+ static quants are available at https://huggingface.co/mradermacher/GodziLLa-30B-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/GodziLLa-30B-i1-GGUF/resolve/main/GodziLLa-30B.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
33
+
34
+
35
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
36
+ types (lower is better):
37
+
38
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
39
+
40
+ And here are Artefact2's thoughts on the matter:
41
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
42
+
43
+ ## Thanks
44
+
45
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
46
+ me use its servers and providing upgrades to my workstation to enable
47
+ this work in my free time.
48
+
49
+ <!-- end -->