Yuxuan Liu commited on
Commit
b185d58
·
1 Parent(s): 94d8ce9

PROSE-FD model weights

Browse files
Files changed (4) hide show
  1. .gitattributes +1 -0
  2. README.md +19 -0
  3. model.png +3 -0
  4. prose_fd.pth +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
+ *png filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,22 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+
5
+ # PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics
6
+
7
+ This folder contains model weights for the PROSE-FD model in paper [PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics](https://arxiv.org/abs/2409.09811). The code is included in: https://github.com/felix-lyx/prose.
8
+
9
+ ![model](model.png)
10
+
11
+ Note: The keys for the weights contain ```module._orig_mod.``` prefixes (coming from DDP and torch.compile). This is automatically taken care of in our code, but worth noting.
12
+
13
+ ## Citation
14
+
15
+ ```
16
+ @article{liu2024prose_fd,
17
+ title={{PROSE-FD}: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics},
18
+ author={Liu, Yuxuan and Sun, Jingmin and He, Xinjie and Pinney, Griffin and Zhang, Zecheng and Schaeffer, Hayden},
19
+ journal={arXiv preprint arXiv:2409.09811},
20
+ year={2024}
21
+ }
22
+ ```
model.png ADDED

Git LFS Details

  • SHA256: 5e0bfec27dfa66f29d71180615acce3ee835cb9b76fbdc574dc231144e274fc1
  • Pointer size: 132 Bytes
  • Size of remote file: 1.11 MB
prose_fd.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa0e65f9be922bbf99dfb5fd1fc0ac072fbcca99574d646db022f1399691bd1
3
+ size 665395159