mradermacher commited on
Commit
51efca3
1 Parent(s): beb400e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -0
README.md CHANGED
@@ -1 +1,48 @@
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/Undi95/Miqu-70B-Alpaca-DPO
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: Undi95/Miqu-70B-Alpaca-DPO
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ ---
8
+ ## About
9
+
10
  static quants of https://huggingface.co/Undi95/Miqu-70B-Alpaca-DPO
11
+
12
+
13
+ <!-- provided-files -->
14
+ 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.
15
+ ## Usage
16
+
17
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
18
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
19
+ more details, including on how to concatenate multi-part files.
20
+
21
+ ## Provided Quants
22
+
23
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
24
+
25
+ | Link | Type | Size/GB | Notes |
26
+ |:-----|:-----|--------:|:------|
27
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.Q2_K.gguf) | Q2_K | 25.9 | |
28
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.Q3_K_M.gguf) | Q3_K_M | 33.7 | lower quality |
29
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.Q4_0.gguf) | Q4_0 | 39.3 | |
30
+ | [GGUF](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.Q4_K_S.gguf) | Q4_K_S | 39.7 | fast, recommended |
31
+ | [PART 1](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Miqu-70B-Alpaca-DPO-GGUF/resolve/main/Miqu-70B-Alpaca-DPO.Q8_0.gguf.part2of2) | Q8_0 | 73.6 | fast, best quality |
32
+
33
+
34
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
35
+ types (lower is better):
36
+
37
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
38
+
39
+ And here are Artefact2's thoughts on the matter:
40
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
41
+
42
+ ## Thanks
43
+
44
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
45
+ me use its servers and providing upgrades to my workstation to enable
46
+ this work in my free time.
47
+
48
+ <!-- end -->