yury-lysogorskiy commited on
Commit
730932b
·
verified ·
1 Parent(s): 39128e1

model card: drop direct-fetch snippet + Versioning section

Browse files
Files changed (1) hide show
  1. README.md +0 -20
README.md CHANGED
@@ -142,26 +142,6 @@ By default all foundation models are stored in `$HOME/.cache/grace`; override wi
142
  **ASE** and **LAMMPS** — see the
143
  [GRACEmaker quickstart](https://github.com/ICAMS/grace-tensorpotential/blob/master/docs/quickstart.md).
144
 
145
- You can also fetch archives directly from this repo:
146
-
147
- ```python
148
- from huggingface_hub import hf_hub_download
149
- path = hf_hub_download(
150
- repo_id="AMS-ICAMS-RUB/grace-foundation-models",
151
- filename="models/GRACE-2L-OMAT-large-base-model.tar.gz",
152
- revision="kk", # immutable tag; "main" is the moving tip
153
- )
154
- ```
155
-
156
- ### Versioning
157
-
158
- Revisions are pinned via immutable git tags so downloads are reproducible:
159
-
160
- - **`uq-v1`** — the initial set of UQ-augmented OMAT foundation models.
161
- - **`kk`** — model archives that additionally bundle the LAMMPS-Kokkos export (`kokkos.npz`).
162
-
163
- `main` always points at the latest revision.
164
-
165
  ---
166
 
167
  ## Fine-tuning foundation models
 
142
  **ASE** and **LAMMPS** — see the
143
  [GRACEmaker quickstart](https://github.com/ICAMS/grace-tensorpotential/blob/master/docs/quickstart.md).
144
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
145
  ---
146
 
147
  ## Fine-tuning foundation models