Align model card naming with ZERITH 2.5
Browse files
README.md
CHANGED
|
@@ -3,12 +3,12 @@ tags:
|
|
| 3 |
- robotics
|
| 4 |
- safetensors
|
| 5 |
---
|
| 6 |
-
#
|
| 7 |
|
| 8 |
-
|
| 9 |
|
| 10 |
The learned tensors retain their original FP32 values. Weights are stored in `model.safetensors`; file size and SHA-256 are recorded in `manifest.json`.
|
| 11 |
|
| 12 |
External VAE, geometry and text-encoder assets must be obtained from the upstream revisions in `dependencies.json`. Text weights and precomputed text embeddings are not included. Generate instruction embeddings using that pinned encoder and the declared token/padding contract.
|
| 13 |
|
| 14 |
-
These are
|
|
|
|
| 3 |
- robotics
|
| 4 |
- safetensors
|
| 5 |
---
|
| 6 |
+
# ZERITH 2.5 LIBERO
|
| 7 |
|
| 8 |
+
ZERITH 2.5 LIBERO policy weights. The deployment manifest contains the architecture, action/camera interfaces and required normalization. Use the settings in inference.json.
|
| 9 |
|
| 10 |
The learned tensors retain their original FP32 values. Weights are stored in `model.safetensors`; file size and SHA-256 are recorded in `manifest.json`.
|
| 11 |
|
| 12 |
External VAE, geometry and text-encoder assets must be obtained from the upstream revisions in `dependencies.json`. Text weights and precomputed text embeddings are not included. Generate instruction embeddings using that pinned encoder and the declared token/padding contract.
|
| 13 |
|
| 14 |
+
These are ZERITH 2.5 artifacts, not Transformers AutoModel checkpoints. Use the matching ZERITH 2.5 neural modules and action interface. A full benchmark rerun with newly generated text embeddings is required before claiming numerical or benchmark equivalence to any previous evaluation.
|