mradermacher commited on
Commit
6ced44e
1 Parent(s): 436abd1

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +71 -0
README.md CHANGED
@@ -1,6 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/FallenMerick/Bionic-Cetacean-20B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: FallenMerick/Bionic-Cetacean-20B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: cc-by-4.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - storywriting
10
+ - text adventure
11
+ - creative
12
+ - story
13
+ - writing
14
+ - fiction
15
+ - roleplaying
16
+ - rp
17
+ - mergekit
18
+ - merge
19
+ ---
20
+ ## About
21
+
22
  <!-- ### quantize_version: 2 -->
23
  <!-- ### output_tensor_quantised: 1 -->
24
  <!-- ### convert_type: hf -->
25
  <!-- ### vocab_type: -->
26
  <!-- ### tags: -->
27
  static quants of https://huggingface.co/FallenMerick/Bionic-Cetacean-20B
28
+
29
+ <!-- provided-files -->
30
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/Bionic-Cetacean-20B-i1-GGUF
31
+ ## Usage
32
+
33
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
34
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
35
+ more details, including on how to concatenate multi-part files.
36
+
37
+ ## Provided Quants
38
+
39
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
40
+
41
+ | Link | Type | Size/GB | Notes |
42
+ |:-----|:-----|--------:|:------|
43
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q2_K.gguf) | Q2_K | 7.5 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.IQ3_XS.gguf) | IQ3_XS | 8.3 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.IQ3_S.gguf) | IQ3_S | 8.8 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q3_K_S.gguf) | Q3_K_S | 8.8 | |
47
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.IQ3_M.gguf) | IQ3_M | 9.3 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q3_K_M.gguf) | Q3_K_M | 9.8 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q3_K_L.gguf) | Q3_K_L | 10.7 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.IQ4_XS.gguf) | IQ4_XS | 10.8 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q4_K_S.gguf) | Q4_K_S | 11.5 | fast, recommended |
52
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q4_K_M.gguf) | Q4_K_M | 12.1 | fast, recommended |
53
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q5_K_S.gguf) | Q5_K_S | 13.9 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q5_K_M.gguf) | Q5_K_M | 14.3 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q6_K.gguf) | Q6_K | 16.5 | very good quality |
56
+ | [GGUF](https://huggingface.co/mradermacher/Bionic-Cetacean-20B-GGUF/resolve/main/Bionic-Cetacean-20B.Q8_0.gguf) | Q8_0 | 21.3 | fast, best quality |
57
+
58
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
59
+ types (lower is better):
60
+
61
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
62
+
63
+ And here are Artefact2's thoughts on the matter:
64
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
65
+
66
+ ## FAQ / Model Request
67
+
68
+ See https://huggingface.co/mradermacher/model_requests for some answers to
69
+ questions you might have and/or if you want some other model quantized.
70
+
71
+ ## Thanks
72
+
73
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
74
+ me use its servers and providing upgrades to my workstation to enable
75
+ this work in my free time.
76
+
77
+ <!-- end -->