mradermacher commited on
Commit
9bd76c2
·
verified ·
1 Parent(s): 367cd41

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -0
README.md CHANGED
@@ -1 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  weighted/imatrix quants of https://huggingface.co/nisten/shqiponja-90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen1.5-72B
4
+ exported_from: nisten/shqiponja-90
5
+ language:
6
+ - en
7
+ library_name: transformers
8
+ license: mit
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - mergekit
12
+ - merge
13
+ ---
14
+ ## About
15
+
16
  weighted/imatrix quants of https://huggingface.co/nisten/shqiponja-90
17
+
18
+
19
+ <!-- provided-files -->
20
+ static quants are available at https://huggingface.co/mradermacher/shqiponja-90-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/shqiponja-90-i1-GGUF/resolve/main/shqiponja-90.i1-Q2_K.gguf) | i1-Q2_K | 35.1 | IQ3_XXS probably better |
34
+ | [GGUF](https://huggingface.co/mradermacher/shqiponja-90-i1-GGUF/resolve/main/shqiponja-90.i1-Q3_K_M.gguf) | i1-Q3_K_M | 45.3 | IQ3_S probably better |
35
+ | [PART 1](https://huggingface.co/mradermacher/shqiponja-90-i1-GGUF/resolve/main/shqiponja-90.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/shqiponja-90-i1-GGUF/resolve/main/shqiponja-90.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 52.7 | optimal size/speed/quality |
36
+ | [PART 1](https://huggingface.co/mradermacher/shqiponja-90-i1-GGUF/resolve/main/shqiponja-90.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/shqiponja-90-i1-GGUF/resolve/main/shqiponja-90.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 55.8 | fast, recommended |
37
+
38
+
39
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
40
+ types (lower is better):
41
+
42
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
43
+
44
+ And here are Artefact2's thoughts on the matter:
45
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
46
+
47
+ ## Thanks
48
+
49
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
50
+ me use its servers and providing upgrades to my workstation to enable
51
+ this work in my free time.
52
+
53
+ <!-- end -->