mradermacher commited on
Commit
f20f4a0
1 Parent(s): 6ab65c6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +57 -0
README.md CHANGED
@@ -1,5 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/digitous/13B-HyperMantis
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: digitous/13B-HyperMantis
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: other
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - llama
10
+ - alpaca
11
+ - vicuna
12
+ - mix
13
+ - merge
14
+ - model merge
15
+ - roleplay
16
+ - chat
17
+ - instruct
18
+ ---
19
+ ## About
20
+
21
  <!-- ### quantize_version: 1 -->
22
  <!-- ### output_tensor_quantised: 1 -->
23
  <!-- ### convert_type: -->
24
  <!-- ### vocab_type: -->
25
  static quants of https://huggingface.co/digitous/13B-HyperMantis
26
+
27
+
28
+ <!-- provided-files -->
29
+ 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.
30
+ ## Usage
31
+
32
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
33
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
34
+ more details, including on how to concatenate multi-part files.
35
+
36
+ ## Provided Quants
37
+
38
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
39
+
40
+ | Link | Type | Size/GB | Notes |
41
+ |:-----|:-----|--------:|:------|
42
+ | [GGUF](https://huggingface.co/mradermacher/13B-HyperMantis-GGUF/resolve/main/13B-HyperMantis.IQ3_S.gguf) | IQ3_S | 5.8 | beats Q3_K* |
43
+ | [GGUF](https://huggingface.co/mradermacher/13B-HyperMantis-GGUF/resolve/main/13B-HyperMantis.IQ3_M.gguf) | IQ3_M | 6.1 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/13B-HyperMantis-GGUF/resolve/main/13B-HyperMantis.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended |
45
+ | [GGUF](https://huggingface.co/mradermacher/13B-HyperMantis-GGUF/resolve/main/13B-HyperMantis.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |
46
+
47
+
48
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
49
+ types (lower is better):
50
+
51
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
52
+
53
+ And here are Artefact2's thoughts on the matter:
54
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
55
+
56
+ ## Thanks
57
+
58
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
59
+ me use its servers and providing upgrades to my workstation to enable
60
+ this work in my free time.
61
+
62
+ <!-- end -->