mradermacher commited on
Commit
9cff67b
1 Parent(s): bc2b8c2

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -0
README.md CHANGED
@@ -1 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  weighted/imatrix quants of https://huggingface.co/MarsupialAI/KitchenSink_103b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: MarsupialAI/KitchenSink_103b
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: llama2
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - rp
10
+ - erp
11
+ - chat
12
+ - storywriting
13
+ ---
14
+ ## About
15
+
16
  weighted/imatrix quants of https://huggingface.co/MarsupialAI/KitchenSink_103b
17
+
18
+
19
+ <!-- provided-files -->
20
+ static quants are available at https://huggingface.co/mradermacher/KitchenSink_103b-GGUF
21
+ ## Usage
22
+
23
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
24
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
25
+ more details, including on how to concatenate multi-part files.
26
+
27
+ ## Provided Quants
28
+
29
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
30
+
31
+ | Link | Type | Size/GB | Notes |
32
+ |:-----|:-----|--------:|:------|
33
+ | [GGUF](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q2_K.gguf) | i1-Q2_K | 38.3 | IQ3_XXS probably better |
34
+ | [PART 1](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 50.0 | IQ3_S probably better |
35
+ | [PART 1](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/KitchenSink_103b-i1-GGUF/resolve/main/KitchenSink_103b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 59.0 | optimal size/speed/quality |
36
+
37
+
38
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
39
+ types (lower is better):
40
+
41
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
42
+
43
+ And here are Artefact2's thoughts on the matter:
44
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
45
+
46
+ ## Thanks
47
+
48
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
49
+ me use its servers and providing upgrades to my workstation to enable
50
+ this work in my free time.
51
+
52
+ <!-- end -->