DavidAU commited on
Commit
d25ce13
1 Parent(s): 3a2b269

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -54
README.md CHANGED
@@ -10,57 +10,3 @@ tags:
10
  - mixture of experts
11
  - merge
12
  ---
13
- ## About
14
-
15
- <!-- ### quantize_version: 2 -->
16
- <!-- ### output_tensor_quantised: 1 -->
17
- <!-- ### convert_type: hf -->
18
- <!-- ### vocab_type: -->
19
- <!-- ### tags: -->
20
- static quants of https://huggingface.co/DavidAU/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B
21
-
22
- <!-- provided-files -->
23
- 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.
24
- ## Usage
25
-
26
- If you are unsure how to use GGUF files, refer to one of [TheBloke's
27
- READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
28
- more details, including on how to concatenate multi-part files.
29
-
30
- ## Provided Quants
31
-
32
- (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
33
-
34
- | Link | Type | Size/GB | Notes |
35
- |:-----|:-----|--------:|:------|
36
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q2_K.gguf) | Q2_K | 9.4 | |
37
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q3_K_S.gguf) | Q3_K_S | 11.0 | |
38
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q3_K_M.gguf) | Q3_K_M | 12.2 | lower quality |
39
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q3_K_L.gguf) | Q3_K_L | 13.1 | |
40
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q4_K_S.gguf) | Q4_K_S | 14.4 | fast, recommended |
41
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q4_K_M.gguf) | Q4_K_M | 15.3 | fast, recommended |
42
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q5_K_S.gguf) | Q5_K_S | 17.3 | |
43
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q5_K_M.gguf) | Q5_K_M | 17.8 | |
44
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q6_K.gguf) | Q6_K | 20.6 | very good quality |
45
- | [GGUF](https://huggingface.co/mradermacher/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B-GGUF/resolve/main/L3-MOE-4x8B-Dark-Planet-Rebel-FURY-25B.Q8_0.gguf) | Q8_0 | 26.6 | fast, best quality |
46
-
47
- Here is a handy graph by ikawrakow comparing some lower-quality quant
48
- types (lower is better):
49
-
50
- ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
51
-
52
- And here are Artefact2's thoughts on the matter:
53
- https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
54
-
55
- ## FAQ / Model Request
56
-
57
- See https://huggingface.co/mradermacher/model_requests for some answers to
58
- questions you might have and/or if you want some other model quantized.
59
-
60
- ## Thanks
61
-
62
- I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
63
- me use its servers and providing upgrades to my workstation to enable
64
- this work in my free time.
65
-
66
- <!-- end -->
 
10
  - mixture of experts
11
  - merge
12
  ---