Upload matgl model

README.md

@@ -4,25 +4,18 @@ tags:
 - matgl
 - materials-science
 - graph-neural-network
-- machine-learning-interatomic-potential
-- foundation-potential
-- mlip
 ---
 
-## Introduction
+# Potential
 
-Pre-trained TensorNet foundation potential, i.e., universal machine learning interatomic potential trained on the MatPES PBE 2025.2 dataset.
-
-## Potential
-
-[matgl](https://github.com/materialsvirtuallab/matgl) `Potential` model (version 3).
+This is a [matgl](https://github.com/materialsvirtuallab/matgl) `Potential` model (version 3).
 
 ## Usage
 
 ```python
 import matgl
 
-model = matgl.load_model("materialyze/TensorNet-PES-MatPES-PBE-2025.2")
+model = matgl.load_model("<owner>/<repo>")
 ```
 
 
@@ -30,6 +23,6 @@ model = matgl.load_model("materialyze/TensorNet-PES-MatPES-PBE-2025.2")
 
 ```json
 {
-  "dataset": "MatPES-r2SCAN-2025.2"
+  "dataset": "MatPES-PBE-2025.2"
 }
 ```

model.json

@@ -1,14 +1,14 @@
 {
     "@class": "Potential",
-    "@module": "matgl.apps.pes",
+    "@module": "matgl.apps._pes_pyg",
     "@model_version": 3,
     "metadata": {
-        "dataset": "MatPES-r2SCAN-2025.2"
+        "dataset": "MatPES-PBE-2025.2"
     },
     "kwargs": {
         "model": {
             "@class": "TensorNet",
-            "@module": "matgl.models",
+            "@module": "matgl.models._tensornet_pyg",
             "@model_version": 2,
             "init_args": {
                 "element_types": [

state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4963f53405b245427a044b7c0fd00ff2e671abdf90ee6c6bfb25f893df336ce2
+oid sha256:b9efa8c708014dd6c37e348f65dc1d8ae5c7bd5c7290de4d9f210e16c7fc3766
 size 3402824