Remove model card README
Browse filesRemove the model introduction; preserve weights, attribution and license files.
README.md
DELETED
|
@@ -1,14 +0,0 @@
|
|
| 1 |
-
# Phoenix Encoders
|
| 2 |
-
|
| 3 |
-
Shared DINO and CSVAE encoders for Phoenix pretraining and Phoenix-MWA.
|
| 4 |
-
|
| 5 |
-
- `dino110k.pt`: existing DINO inference weights, unchanged.
|
| 6 |
-
- `csvae.pt`: CSVAE weights; `model_type=causal_semantic_vae`, `format_version=2`.
|
| 7 |
-
|
| 8 |
-
CSVAE retains the original model configuration and all 118 tensor values. Use the matching CSVAE code (`dino_csvae`, `csvae_encoder`, `csvae`) and `CSVAE_CHECKPOINT` / `--csvae` interfaces. The saved training step is metadata, not part of the filename.
|
| 9 |
-
|
| 10 |
-
Previous release revision: [`07d7189d56c45ffb5ace1472b2023242d85584ec`](https://huggingface.co/OpenPhoenix/Phoenix-Encoders/tree/07d7189d56c45ffb5ace1472b2023242d85584ec). Use that revision when reproducing the previous code interface.
|
| 11 |
-
|
| 12 |
-
Current `csvae.pt` SHA-256: `fbb4d3f32309b77a5f068634816752d4497fb01798c4be2292bb25690f5baafd`.
|
| 13 |
-
|
| 14 |
-
See [NOTICE.md](NOTICE.md) and the included licenses for attribution and license scope. This metadata migration does not change any license grant.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|