Transformers
GGUF
English
Not-For-All-Audiences
Inference Endpoints
mradermacher commited on
Commit
ec2296e
1 Parent(s): 2b6234d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -0
README.md CHANGED
@@ -1 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  weighted/imatrix quants of https://huggingface.co/jondurbin/spicyboros-70b-2.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ datasets:
3
+ - jondurbin/airoboros-2.2
4
+ exported_from: jondurbin/spicyboros-70b-2.2
5
+ language:
6
+ - en
7
+ library_name: transformers
8
+ license: llama2
9
+ quantized_by: mradermacher
10
+ tags:
11
+ - not-for-all-audiences
12
+ ---
13
+ ## About
14
+
15
  weighted/imatrix quants of https://huggingface.co/jondurbin/spicyboros-70b-2.2
16
+
17
+
18
+ <!-- provided-files -->
19
+ static quants are available at https://huggingface.co/mradermacher/spicyboros-70b-2.2-GGUF
20
+ ## Usage
21
+
22
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
23
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
24
+ more details, including on how to concatenate multi-part files.
25
+
26
+ ## Provided Quants
27
+
28
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
29
+
30
+ | Link | Type | Size/GB | Notes |
31
+ |:-----|:-----|--------:|:------|
32
+ | [GGUF](https://huggingface.co/mradermacher/spicyboros-70b-2.2-i1-GGUF/resolve/main/spicyboros-70b-2.2.i1-Q2_K.gguf) | i1-Q2_K | 25.9 | IQ3_XXS probably better |
33
+ | [GGUF](https://huggingface.co/mradermacher/spicyboros-70b-2.2-i1-GGUF/resolve/main/spicyboros-70b-2.2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 33.7 | IQ3_S probably better |
34
+ | [GGUF](https://huggingface.co/mradermacher/spicyboros-70b-2.2-i1-GGUF/resolve/main/spicyboros-70b-2.2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 39.7 | optimal size/speed/quality |
35
+ | [GGUF](https://huggingface.co/mradermacher/spicyboros-70b-2.2-i1-GGUF/resolve/main/spicyboros-70b-2.2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 41.8 | fast, recommended |
36
+ | [PART 1](https://huggingface.co/mradermacher/spicyboros-70b-2.2-i1-GGUF/resolve/main/spicyboros-70b-2.2.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/spicyboros-70b-2.2-i1-GGUF/resolve/main/spicyboros-70b-2.2.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 57.0 | practically like static Q6_K |
37
+
38
+
39
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
40
+ types (lower is better):
41
+
42
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
43
+
44
+ And here are Artefact2's thoughts on the matter:
45
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
46
+
47
+ ## Thanks
48
+
49
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
50
+ me use its servers and providing upgrades to my workstation to enable
51
+ this work in my free time.
52
+
53
+ <!-- end -->