mradermacher commited on
Commit
f032161
1 Parent(s): e1e1e71

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -0
README.md CHANGED
@@ -1 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/Eurdem/megatron_v4_4x7B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ exported_from: Eurdem/megatron_v4_4x7B
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - moe
10
+ - merge
11
+ ---
12
+ ## About
13
+
14
  static quants of https://huggingface.co/Eurdem/megatron_v4_4x7B
15
+
16
+
17
+ <!-- provided-files -->
18
+ 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.
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/megatron_v4_4x7B-GGUF/resolve/main/megatron_v4_4x7B.Q2_K.gguf) | Q2_K | 9.1 | |
32
+ | [GGUF](https://huggingface.co/mradermacher/megatron_v4_4x7B-GGUF/resolve/main/megatron_v4_4x7B.IQ3_S.gguf) | IQ3_S | 10.7 | beats Q3_K* |
33
+ | [GGUF](https://huggingface.co/mradermacher/megatron_v4_4x7B-GGUF/resolve/main/megatron_v4_4x7B.Q3_K_M.gguf) | Q3_K_M | 11.8 | lower quality |
34
+ | [GGUF](https://huggingface.co/mradermacher/megatron_v4_4x7B-GGUF/resolve/main/megatron_v4_4x7B.Q4_0.gguf) | Q4_0 | 13.9 | |
35
+ | [GGUF](https://huggingface.co/mradermacher/megatron_v4_4x7B-GGUF/resolve/main/megatron_v4_4x7B.Q4_K_S.gguf) | Q4_K_S | 14.0 | fast, recommended |
36
+ | [GGUF](https://huggingface.co/mradermacher/megatron_v4_4x7B-GGUF/resolve/main/megatron_v4_4x7B.Q8_0.gguf) | Q8_0 | 25.9 | fast, best quality |
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 -->