Transformers
GGUF
English
Inference Endpoints
mradermacher commited on
Commit
3aca961
1 Parent(s): 83d6be5

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +59 -0
README.md CHANGED
@@ -1,5 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/Fredithefish/Guanaco-13B-Uncensored
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - Fredithefish/openassistant-guanaco-unfiltered
4
+ exported_from: Fredithefish/Guanaco-13B-Uncensored
5
+ language:
6
+ - en
7
+ library_name: transformers
8
+ license: apache-2.0
9
+ quantized_by: mradermacher
10
+ ---
11
+ ## About
12
+
13
  <!-- ### quantize_version: 1 -->
14
  <!-- ### output_tensor_quantised: 1 -->
15
  <!-- ### convert_type: -->
16
  <!-- ### vocab_type: -->
17
  static quants of https://huggingface.co/Fredithefish/Guanaco-13B-Uncensored
18
+
19
+
20
+ <!-- provided-files -->
21
+ 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.
22
+ ## Usage
23
+
24
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
25
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
26
+ more details, including on how to concatenate multi-part files.
27
+
28
+ ## Provided Quants
29
+
30
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
31
+
32
+ | Link | Type | Size/GB | Notes |
33
+ |:-----|:-----|--------:|:------|
34
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q2_K.gguf) | Q2_K | 5.0 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.IQ3_XS.gguf) | IQ3_XS | 5.5 | |
36
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.IQ3_S.gguf) | IQ3_S | 5.8 | beats Q3_K* |
37
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q3_K_S.gguf) | Q3_K_S | 5.8 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.IQ3_M.gguf) | IQ3_M | 6.1 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q3_K_M.gguf) | Q3_K_M | 6.4 | lower quality |
40
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q3_K_L.gguf) | Q3_K_L | 7.0 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.IQ4_XS.gguf) | IQ4_XS | 7.1 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q4_K_S.gguf) | Q4_K_S | 7.5 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q4_K_M.gguf) | Q4_K_M | 8.0 | fast, recommended |
44
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q5_K_S.gguf) | Q5_K_S | 9.1 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q5_K_M.gguf) | Q5_K_M | 9.3 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q6_K.gguf) | Q6_K | 10.8 | very good quality |
47
+ | [GGUF](https://huggingface.co/mradermacher/Guanaco-13B-Uncensored-GGUF/resolve/main/Guanaco-13B-Uncensored.Q8_0.gguf) | Q8_0 | 13.9 | fast, best quality |
48
+
49
+
50
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
51
+ types (lower is better):
52
+
53
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
54
+
55
+ And here are Artefact2's thoughts on the matter:
56
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
57
+
58
+ ## Thanks
59
+
60
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
61
+ me use its servers and providing upgrades to my workstation to enable
62
+ this work in my free time.
63
+
64
+ <!-- end -->