mradermacher commited on
Commit
5a61609
1 Parent(s): a3540ff

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +50 -0
README.md CHANGED
@@ -1 +1,51 @@
 
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/mlabonne/UltraMerge-7B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: mlabonne/UltraMerge-7B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ quantized_by: mradermacher
8
+ ---
9
+ ## About
10
+
11
  static quants of https://huggingface.co/mlabonne/UltraMerge-7B
12
+
13
+
14
+ <!-- provided-files -->
15
+ 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.
16
+ ## Usage
17
+
18
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
19
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
20
+ more details, including on how to concatenate multi-part files.
21
+
22
+ ## Provided Quants
23
+
24
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
25
+
26
+ | Link | Type | Size/GB | Notes |
27
+ |:-----|:-----|--------:|:------|
28
+ | [GGUF](https://huggingface.co/mradermacher/UltraMerge-7B-GGUF/resolve/main/UltraMerge-7B.Q2_K.gguf) | Q2_K | 3.0 | |
29
+ | [GGUF](https://huggingface.co/mradermacher/UltraMerge-7B-GGUF/resolve/main/UltraMerge-7B.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
30
+ | [GGUF](https://huggingface.co/mradermacher/UltraMerge-7B-GGUF/resolve/main/UltraMerge-7B.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
31
+ | [GGUF](https://huggingface.co/mradermacher/UltraMerge-7B-GGUF/resolve/main/UltraMerge-7B.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/UltraMerge-7B-GGUF/resolve/main/UltraMerge-7B.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
33
+ | [GGUF](https://huggingface.co/mradermacher/UltraMerge-7B-GGUF/resolve/main/UltraMerge-7B.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
34
+ | [GGUF](https://huggingface.co/mradermacher/UltraMerge-7B-GGUF/resolve/main/UltraMerge-7B.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
35
+
36
+
37
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
38
+ types (lower is better):
39
+
40
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
41
+
42
+ And here are Artefact2's thoughts on the matter:
43
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
44
+
45
+ ## Thanks
46
+
47
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
48
+ me use its servers and providing upgrades to my workstation to enable
49
+ this work in my free time.
50
+
51
+ <!-- end -->