mradermacher commited on
Commit
3bb918c
·
verified ·
1 Parent(s): f684047

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +60 -0
README.md CHANGED
@@ -1,6 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  <!-- ### quantize_version: 2 -->
2
  <!-- ### output_tensor_quantised: 1 -->
3
  <!-- ### convert_type: hf -->
4
  <!-- ### vocab_type: -->
5
  <!-- ### tags: -->
6
  static quants of https://huggingface.co/Snowflake/snowflake-arctic-instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Snowflake/snowflake-arctic-instruct
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ license: apache-2.0
7
+ quantized_by: mradermacher
8
+ tags:
9
+ - snowflake
10
+ - arctic
11
+ - moe
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/Snowflake/snowflake-arctic-instruct
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
+ | [PART 1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q2_K.gguf.part4of4) | Q2_K | 173.7 | |
37
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_S.gguf.part5of5) | Q3_K_S | 205.9 | |
38
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_M.gguf.part1of5) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_M.gguf.part2of5) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_M.gguf.part3of5) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_M.gguf.part4of5) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_M.gguf.part5of5) | Q3_K_M | 228.3 | lower quality |
39
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_L.gguf.part1of6) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_L.gguf.part2of6) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_L.gguf.part3of6) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_L.gguf.part4of6) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_L.gguf.part5of6) [P6](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q3_K_L.gguf.part6of6) | Q3_K_L | 247.2 | |
40
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_S.gguf.part1of6) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_S.gguf.part2of6) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_S.gguf.part3of6) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_S.gguf.part4of6) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_S.gguf.part5of6) [P6](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_S.gguf.part6of6) | Q4_K_S | 271.7 | fast, recommended |
41
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_M.gguf.part1of6) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_M.gguf.part2of6) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_M.gguf.part3of6) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_M.gguf.part4of6) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_M.gguf.part5of6) [P6](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q4_K_M.gguf.part6of6) | Q4_K_M | 289.3 | fast, recommended |
42
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_S.gguf.part1of7) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_S.gguf.part2of7) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_S.gguf.part3of7) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_S.gguf.part4of7) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_S.gguf.part5of7) [P6](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_S.gguf.part6of7) [P7](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_S.gguf.part7of7) | Q5_K_S | 329.3 | |
43
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_M.gguf.part1of7) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_M.gguf.part2of7) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_M.gguf.part3of7) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_M.gguf.part4of7) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_M.gguf.part5of7) [P6](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_M.gguf.part6of7) [P7](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q5_K_M.gguf.part7of7) | Q5_K_M | 339.5 | |
44
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q6_K.gguf.part1of8) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q6_K.gguf.part2of8) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q6_K.gguf.part3of8) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q6_K.gguf.part4of8) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q6_K.gguf.part5of8) [P6](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q6_K.gguf.part6of8) [P7](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q6_K.gguf.part7of8) [P8](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q6_K.gguf.part8of8) | Q6_K | 392.8 | very good quality |
45
+ | [P1](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part01of11) [P2](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part02of11) [P3](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part03of11) [P4](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part04of11) [P5](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part05of11) [P6](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part06of11) [P7](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part07of11) [P8](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part08of11) [P9](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part09of11) [P10](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part10of11) [P11](https://huggingface.co/mradermacher/snowflake-arctic-instruct-GGUF/resolve/main/snowflake-arctic-instruct.Q8_0.gguf.part11of11) | Q8_0 | 508.7 | 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 -->