mradermacher commited on
Commit
5d632fd
·
verified ·
1 Parent(s): 15dafe5

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +47 -0
README.md CHANGED
@@ -1,5 +1,52 @@
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 1 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: -->
4
  <!-- ### vocab_type: -->
5
  weighted/imatrix quants of https://huggingface.co/GritLM/GritLM-8x7B-KTO
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: GritLM/GritLM-8x7B-KTO
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ quantized_by: mradermacher
7
+ ---
8
+ ## About
9
+
10
  <!-- ### quantize_version: 1 -->
11
  <!-- ### output_tensor_quantised: 1 -->
12
  <!-- ### convert_type: -->
13
  <!-- ### vocab_type: -->
14
  weighted/imatrix quants of https://huggingface.co/GritLM/GritLM-8x7B-KTO
15
+
16
+
17
+ <!-- provided-files -->
18
+ static quants are available at https://huggingface.co/mradermacher/GritLM-8x7B-KTO-GGUF
19
+ ## Usage
20
+
21
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
22
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
23
+ more details, including on how to concatenate multi-part files.
24
+
25
+ ## Provided Quants
26
+
27
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
28
+
29
+ | Link | Type | Size/GB | Notes |
30
+ |:-----|:-----|--------:|:------|
31
+ | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
32
+ | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
33
+ | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
34
+ | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
35
+ | [GGUF](https://huggingface.co/mradermacher/GritLM-8x7B-KTO-i1-GGUF/resolve/main/GritLM-8x7B-KTO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
36
+
37
+
38
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
39
+ types (lower is better):
40
+
41
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
42
+
43
+ And here are Artefact2's thoughts on the matter:
44
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
45
+
46
+ ## Thanks
47
+
48
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
49
+ me use its servers and providing upgrades to my workstation to enable
50
+ this work in my free time.
51
+
52
+ <!-- end -->