mradermacher commited on
Commit
2274729
1 Parent(s): ad6ef6e

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md CHANGED
@@ -1 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  static quants of https://huggingface.co/automerger/MeliodasT3q-7B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - AurelPx/Meliodas-7b-dare
4
+ - chihoonlee10/T3Q-Mistral-Orca-Math-DPO
5
+ exported_from: automerger/MeliodasT3q-7B
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ license: apache-2.0
10
+ quantized_by: mradermacher
11
+ tags:
12
+ - merge
13
+ - mergekit
14
+ - lazymergekit
15
+ - automerger
16
+ ---
17
+ ## About
18
+
19
  static quants of https://huggingface.co/automerger/MeliodasT3q-7B
20
+
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/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q2_K.gguf) | Q2_K | 3.0 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.IQ3_XS.gguf) | IQ3_XS | 3.3 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q3_K_S.gguf) | Q3_K_S | 3.4 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.IQ3_S.gguf) | IQ3_S | 3.4 | beats Q3_K* |
40
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.IQ3_M.gguf) | IQ3_M | 3.5 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
42
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q4_0.gguf) | Q4_0 | 4.4 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
46
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.IQ4_NL.gguf) | IQ4_NL | 4.4 | slightly worse than Q4_K_S |
47
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended |
48
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
51
+ | [GGUF](https://huggingface.co/mradermacher/MeliodasT3q-7B-GGUF/resolve/main/MeliodasT3q-7B.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality |
52
+
53
+
54
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
55
+ types (lower is better):
56
+
57
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
58
+
59
+ And here are Artefact2's thoughts on the matter:
60
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
61
+
62
+ ## Thanks
63
+
64
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
65
+ me use its servers and providing upgrades to my workstation to enable
66
+ this work in my free time.
67
+
68
+ <!-- end -->