mradermacher commited on
Commit
0fa2110
·
verified ·
1 Parent(s): e024005

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +77 -0
README.md CHANGED
@@ -1,5 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/Joseph717171/ANIMA-Phi-Neptune-Mistral-10.7B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ datasets:
4
+ - Severian/Biomimicry
5
+ - emrgnt-cmplxty/sciphi-textbooks-are-all-you-need
6
+ - fmars/wiki_stem
7
+ - fblgit/tree-of-knowledge
8
+ - Severian/Bio-Design-Process
9
+ exported_from: Joseph717171/ANIMA-Phi-Neptune-Mistral-10.7B
10
+ language:
11
+ - en
12
+ library_name: transformers
13
+ license: artistic-2.0
14
+ quantized_by: mradermacher
15
+ tags:
16
+ - mergekit
17
+ - merge
18
+ - chemistry
19
+ - biology
20
+ - climate
21
+ - science
22
+ - philosophy
23
+ - nature
24
+ - ecology
25
+ - biomimicry
26
+ - fauna
27
+ - flora
28
+ ---
29
+ ## About
30
+
31
  <!-- ### quantize_version: 1 -->
32
  <!-- ### output_tensor_quantised: 1 -->
33
  <!-- ### convert_type: -->
34
  <!-- ### vocab_type: -->
35
  static quants of https://huggingface.co/Joseph717171/ANIMA-Phi-Neptune-Mistral-10.7B
36
+
37
+
38
+ <!-- provided-files -->
39
+ 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.
40
+ ## Usage
41
+
42
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
43
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
44
+ more details, including on how to concatenate multi-part files.
45
+
46
+ ## Provided Quants
47
+
48
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
49
+
50
+ | Link | Type | Size/GB | Notes |
51
+ |:-----|:-----|--------:|:------|
52
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q2_K.gguf) | Q2_K | 4.1 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.IQ3_XS.gguf) | IQ3_XS | 4.5 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q3_K_S.gguf) | Q3_K_S | 4.8 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.IQ3_S.gguf) | IQ3_S | 4.8 | beats Q3_K* |
56
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.IQ3_M.gguf) | IQ3_M | 4.9 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q3_K_M.gguf) | Q3_K_M | 5.3 | lower quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q3_K_L.gguf) | Q3_K_L | 5.8 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.IQ4_XS.gguf) | IQ4_XS | 5.9 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q4_K_S.gguf) | Q4_K_S | 6.2 | fast, recommended |
61
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q4_K_M.gguf) | Q4_K_M | 6.6 | fast, recommended |
62
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q5_K_S.gguf) | Q5_K_S | 7.5 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q5_K_M.gguf) | Q5_K_M | 7.7 | |
64
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q6_K.gguf) | Q6_K | 8.9 | very good quality |
65
+ | [GGUF](https://huggingface.co/mradermacher/ANIMA-Phi-Neptune-Mistral-10.7B-GGUF/resolve/main/ANIMA-Phi-Neptune-Mistral-10.7B.Q8_0.gguf) | Q8_0 | 11.5 | fast, best quality |
66
+
67
+
68
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
69
+ types (lower is better):
70
+
71
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
72
+
73
+ And here are Artefact2's thoughts on the matter:
74
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
75
+
76
+ ## Thanks
77
+
78
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
79
+ me use its servers and providing upgrades to my workstation to enable
80
+ this work in my free time.
81
+
82
+ <!-- end -->