Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ This is a scaled-up version of the checkpoint originally presented in our prepri
|
|
| 11 |
Trained with larger dataset of multiple initial conditions per system, with mixed periods as well.
|
| 12 |
Specifically, we include 8 out of the 16 initial conditions (ICs) per system that we provide in our https://huggingface.co/datasets/GilpinLab/skew-mixedp-ic16, in addition to other datasets.
|
| 13 |
|
| 14 |
-
We provide a full reproduction of the dataset used to train Panda-72M, in https://huggingface.co/datasets/GilpinLab/dataset-panda72M-repro
|
| 15 |
|
| 16 |
We trained this model for 800k iterations, with per-device batch size 384, across 6 AMD MI100X GPUs.
|
| 17 |
*Panda*: Patched Attention for Nonlinear Dynamics.
|
|
|
|
| 11 |
Trained with larger dataset of multiple initial conditions per system, with mixed periods as well.
|
| 12 |
Specifically, we include 8 out of the 16 initial conditions (ICs) per system that we provide in our https://huggingface.co/datasets/GilpinLab/skew-mixedp-ic16, in addition to other datasets.
|
| 13 |
|
| 14 |
+
We provide a **full reproduction of the dataset** used to train Panda-72M, in https://huggingface.co/datasets/GilpinLab/dataset-panda72M-repro
|
| 15 |
|
| 16 |
We trained this model for 800k iterations, with per-device batch size 384, across 6 AMD MI100X GPUs.
|
| 17 |
*Panda*: Patched Attention for Nonlinear Dynamics.
|