mradermacher commited on
Commit
350e21e
·
verified ·
1 Parent(s): 18953cb

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +48 -0
README.md CHANGED
@@ -1 +1,49 @@
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/sequelbox/SpellBlade
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: transformers
5
+ license: apache-2.0
6
+ quantized_by: mradermacher
7
+ ---
8
+ ## About
9
+
10
  static quants of https://huggingface.co/sequelbox/SpellBlade
11
+
12
+
13
+ <!-- provided-files -->
14
+ ## Usage
15
+
16
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
17
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
18
+ more details, including on how to concatenate multi-part files.
19
+
20
+ ## Provided Quants
21
+
22
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
23
+
24
+ | Link | Type | Size/GB | Notes |
25
+ |:-----|:-----|--------:|:------|
26
+ | [GGUF](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q2_K.gguf) | Q2_K | 26.4 | |
27
+ | [GGUF](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q3_K_S.gguf) | Q3_K_S | 30.9 | |
28
+ | [GGUF](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q3_K_M.gguf) | Q3_K_M | 34.2 | lower quality |
29
+ | [GGUF](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q3_K_L.gguf) | Q3_K_L | 37.1 | |
30
+ | [GGUF](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q4_K_S.gguf) | Q4_K_S | 40.2 | fast, medium quality |
31
+ | [PART 1](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q6_K.gguf.part2of2) | Q6_K | 57.5 | very good quality |
32
+ | [PART 1](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/SpellBlade-GGUF/resolve/main/SpellBlade.Q8_0.gguf.part2of2) | Q8_0 | 74.2 | fast, best quality |
33
+
34
+
35
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
36
+ types (lower is better):
37
+
38
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
39
+
40
+ And here are Artefact2's thoughts on the matter:
41
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
42
+
43
+ ## Thanks
44
+
45
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
46
+ me use its servers and providing upgrades to my workstation to enable
47
+ this work in my free time.
48
+
49
+ <!-- end -->