mradermacher commited on
Commit
c9ba163
1 Parent(s): 1b27b06

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +76 -0
README.md CHANGED
@@ -1,6 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/sail/Sailor-7B
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sail/Sailor-7B
3
+ datasets:
4
+ - cerebras/SlimPajama-627B
5
+ - Skywork/SkyPile-150B
6
+ - allenai/MADLAD-400
7
+ - cc100
8
+ language:
9
+ - en
10
+ - zh
11
+ - id
12
+ - th
13
+ - vi
14
+ - ms
15
+ - lo
16
+ library_name: transformers
17
+ license: apache-2.0
18
+ quantized_by: mradermacher
19
+ tags:
20
+ - multilingual
21
+ - sea
22
+ - sailor
23
+ ---
24
+ ## About
25
+
26
  <!-- ### quantize_version: 2 -->
27
  <!-- ### output_tensor_quantised: 1 -->
28
  <!-- ### convert_type: hf -->
29
  <!-- ### vocab_type: -->
30
  <!-- ### tags: -->
31
  static quants of https://huggingface.co/sail/Sailor-7B
32
+
33
+ <!-- provided-files -->
34
+ 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.
35
+ ## Usage
36
+
37
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
38
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
39
+ more details, including on how to concatenate multi-part files.
40
+
41
+ ## Provided Quants
42
+
43
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
44
+
45
+ | Link | Type | Size/GB | Notes |
46
+ |:-----|:-----|--------:|:------|
47
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q2_K.gguf) | Q2_K | 3.2 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.IQ3_XS.gguf) | IQ3_XS | 3.5 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.IQ3_S.gguf) | IQ3_S | 3.7 | beats Q3_K* |
50
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q3_K_S.gguf) | Q3_K_S | 3.7 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.IQ3_M.gguf) | IQ3_M | 3.8 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q3_K_L.gguf) | Q3_K_L | 4.3 | |
54
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended |
57
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q5_K_S.gguf) | Q5_K_S | 5.5 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q5_K_M.gguf) | Q5_K_M | 5.6 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
60
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality |
61
+ | [GGUF](https://huggingface.co/mradermacher/Sailor-7B-GGUF/resolve/main/Sailor-7B.f16.gguf) | f16 | 15.5 | 16 bpw, overkill |
62
+
63
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
64
+ types (lower is better):
65
+
66
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
67
+
68
+ And here are Artefact2's thoughts on the matter:
69
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
70
+
71
+ ## FAQ / Model Request
72
+
73
+ See https://huggingface.co/mradermacher/model_requests for some answers to
74
+ questions you might have and/or if you want some other model quantized.
75
+
76
+ ## Thanks
77
+
78
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
79
+ me use its servers and providing upgrades to my workstation to enable
80
+ this work in my free time.
81
+
82
+ <!-- end -->