mradermacher commited on
Commit
5dfcebd
1 Parent(s): d0a7f4c

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +61 -0
README.md CHANGED
@@ -1,3 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### convert_type: -->
2
  <!-- ### vocab_type: -->
3
  static quants of https://huggingface.co/louisbrulenaudet/DevPearl-2x7B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - deepseek-ai/deepseek-coder-6.7b-instruct
4
+ - defog/sqlcoder-7b-2
5
+ exported_from: louisbrulenaudet/DevPearl-2x7B
6
+ language:
7
+ - en
8
+ library_name: transformers
9
+ license: cc-by-sa-4.0
10
+ quantized_by: mradermacher
11
+ tags:
12
+ - moe
13
+ - merge
14
+ - mergekit
15
+ - lazymergekit
16
+ - deepseek-ai/deepseek-coder-6.7b-instruct
17
+ - defog/sqlcoder-7b-2
18
+ - Python
19
+ - Javascript
20
+ - sql
21
+ ---
22
+ ## About
23
+
24
  <!-- ### convert_type: -->
25
  <!-- ### vocab_type: -->
26
  static quants of https://huggingface.co/louisbrulenaudet/DevPearl-2x7B
27
+
28
+
29
+ <!-- provided-files -->
30
+ 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.
31
+ ## Usage
32
+
33
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
34
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
35
+ more details, including on how to concatenate multi-part files.
36
+
37
+ ## Provided Quants
38
+
39
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
40
+
41
+ | Link | Type | Size/GB | Notes |
42
+ |:-----|:-----|--------:|:------|
43
+ | [GGUF](https://huggingface.co/mradermacher/DevPearl-2x7B-GGUF/resolve/main/DevPearl-2x7B.Q2_K.gguf) | Q2_K | 4.4 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/DevPearl-2x7B-GGUF/resolve/main/DevPearl-2x7B.IQ3_S.gguf) | IQ3_S | 5.1 | beats Q3_K* |
45
+ | [GGUF](https://huggingface.co/mradermacher/DevPearl-2x7B-GGUF/resolve/main/DevPearl-2x7B.Q3_K_M.gguf) | Q3_K_M | 5.6 | lower quality |
46
+ | [GGUF](https://huggingface.co/mradermacher/DevPearl-2x7B-GGUF/resolve/main/DevPearl-2x7B.Q4_K_S.gguf) | Q4_K_S | 6.6 | fast, recommended |
47
+ | [GGUF](https://huggingface.co/mradermacher/DevPearl-2x7B-GGUF/resolve/main/DevPearl-2x7B.Q8_0.gguf) | Q8_0 | 12.0 | fast, best quality |
48
+
49
+
50
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
51
+ types (lower is better):
52
+
53
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
54
+
55
+ And here are Artefact2's thoughts on the matter:
56
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
57
+
58
+ ## Thanks
59
+
60
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
61
+ me use its servers and providing upgrades to my workstation to enable
62
+ this work in my free time.
63
+
64
+ <!-- end -->