mradermacher commited on
Commit
da40a04
1 Parent(s): 3f8e7a9

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md CHANGED
@@ -1,5 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  static quants of https://huggingface.co/eldogbbhed/Wiz2Beagle-7b-v1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: eldogbbhed/Wiz2Beagle-7b-v1
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - merge
10
+ - mergekit
11
+ - vortexmergekit
12
+ - amazingvince/Not-WizardLM-2-7B
13
+ - mlabonne/NeuralBeagle14-7B
14
+ ---
15
+ ## About
16
+
17
  <!-- ### quantize_version: 1 -->
18
  <!-- ### output_tensor_quantised: 1 -->
19
  <!-- ### convert_type: -->
20
  <!-- ### vocab_type: -->
21
  static quants of https://huggingface.co/eldogbbhed/Wiz2Beagle-7b-v1
22
+
23
+
24
+ <!-- provided-files -->
25
+ 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.
26
+ ## Usage
27
+
28
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
29
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
30
+ more details, including on how to concatenate multi-part files.
31
+
32
+ ## Provided Quants
33
+
34
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
35
+
36
+ | Link | Type | Size/GB | Notes |
37
+ |:-----|:-----|--------:|:------|
38
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q2_K.gguf) | Q2_K | 2.8 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.IQ3_XS.gguf) | IQ3_XS | 3.1 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q3_K_S.gguf) | Q3_K_S | 3.3 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.IQ3_S.gguf) | IQ3_S | 3.3 | beats Q3_K* |
42
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.IQ3_M.gguf) | IQ3_M | 3.4 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
44
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q3_K_L.gguf) | Q3_K_L | 3.9 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.IQ4_XS.gguf) | IQ4_XS | 4.0 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q5_K_S.gguf) | Q5_K_S | 5.1 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q5_K_M.gguf) | Q5_K_M | 5.2 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q6_K.gguf) | Q6_K | 6.0 | very good quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/Wiz2Beagle-7b-v1-GGUF/resolve/main/Wiz2Beagle-7b-v1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality |
52
+
53
+
54
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
55
+ types (lower is better):
56
+
57
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
58
+
59
+ And here are Artefact2's thoughts on the matter:
60
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
61
+
62
+ ## Thanks
63
+
64
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
65
+ me use its servers and providing upgrades to my workstation to enable
66
+ this work in my free time.
67
+
68
+ <!-- end -->