Ayush commited on
Commit
5d7a6b1
·
verified ·
1 Parent(s): 8c835b9

Add files using upload-large-folder tool

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. README.md +66 -0
  3. fuxi_s2s +3 -0
  4. fuxi_s2s.onnx +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ fuxi_s2s filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-nd-4.0
3
+ library_name: onnxruntime
4
+ tags:
5
+ - climate
6
+ - onnx
7
+ - seasonal
8
+ - subseasonal
9
+ - weather
10
+ ---
11
+
12
+ # FuXi-S2S ONNX checkpoint mirror
13
+
14
+ This repository is an unchanged convenience mirror of the official FuXi-S2S
15
+ ONNX checkpoint published by the FuXi Team. The authoritative release remains
16
+ the [Zenodo record](https://zenodo.org/records/15718402), and model usage is
17
+ documented in the [official FuXi-S2S repository](https://github.com/tpys/FuXi-S2S).
18
+
19
+ The mirror exists so downstream integrations such as
20
+ [NVIDIA Earth2Studio](https://github.com/NVIDIA/earth2studio) can retrieve the
21
+ ONNX graph and its large external-data file reliably and pin an immutable
22
+ revision.
23
+
24
+ ## Files and provenance
25
+
26
+ The two files were extracted without modification from `model-1.0.tar` in the
27
+ official Zenodo release. They must remain in the same directory because the
28
+ ONNX graph refers to its external weights by the sibling filename
29
+ `fuxi_s2s`.
30
+
31
+ | File | Size (bytes) | SHA-256 |
32
+ | --- | ---: | --- |
33
+ | `fuxi_s2s.onnx` | 1,588,847 | `bcc3419ef698cb894b17fae2c5e40ded05d87ed8d4ba9f6342c9f0afff3c70f5` |
34
+ | `fuxi_s2s` | 2,078,823,204 | `628d86076810d3d5c53a7a27f10e67b08051e2d2e5c9224a2df96cba8ecd8ea8` |
35
+
36
+ The source archive is 2,080,419,840 bytes with MD5 checksum
37
+ `17790f6bb7c3f83ce846d36f2339c4b3`, matching the checksum published by
38
+ Zenodo. The separate `data.zip` validation sample is intentionally not
39
+ mirrored here and remains available from the authoritative record.
40
+
41
+ ## License and use restrictions
42
+
43
+ The checkpoint is licensed under
44
+ [CC BY-NC-ND 4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/).
45
+ The official record states that it is intended for research use and that
46
+ commercial or competition use requires prior permission from the authors.
47
+ Those checkpoint terms apply independently of the license of any downstream
48
+ integration.
49
+
50
+ ## Citation
51
+
52
+ If you use this checkpoint, cite the original work:
53
+
54
+ ```bibtex
55
+ @article{chen2024machine,
56
+ title = {A machine learning model that outperforms conventional global subseasonal forecast models},
57
+ author = {Chen, Lei and Zhong, Xiaohui and Li, Hao and Wu, Jie and Lu, Bo and Chen, Deliang and Xie, Shang-Ping and Wu, Libo and Chao, Qingchen and Lin, Chensen and others},
58
+ journal = {Nature Communications},
59
+ volume = {15},
60
+ number = {6425},
61
+ pages = {1--14},
62
+ year = {2024},
63
+ publisher = {Nature Publishing Group UK London},
64
+ doi = {10.1038/s41467-024-50714-1}
65
+ }
66
+ ```
fuxi_s2s ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:628d86076810d3d5c53a7a27f10e67b08051e2d2e5c9224a2df96cba8ecd8ea8
3
+ size 2078823204
fuxi_s2s.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc3419ef698cb894b17fae2c5e40ded05d87ed8d4ba9f6342c9f0afff3c70f5
3
+ size 1588847