Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)

README.md

@@ -1,76 +1,76 @@
----
-pipeline_tag: image-feature-extraction
-license: apache-2.0
-base_model: facebook/dinov2-small
-library_name: kerasformers
-tags:
-- keras
-- kerasformers
-- dinov2
-- feature-extraction
-- vision
-- arxiv:2304.07193
-- pytorch
-- jax
-- tf
----
-
-## ***See [our collection](https://huggingface.co/collections/kerasformers/dino-v1-v2-v3-6a6a94f8281a2f373f70e769) for all versions of DINOv2.***
-
-# Run DINOv2 with Keras 3: JAX, PyTorch, or TensorFlow
-
-[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-DINOv2-blue)](https://imvision12.github.io/KerasFormers/dinov2/) [![Collection](https://img.shields.io/badge/HF-DINOv2%20collection-yellow)](https://huggingface.co/collections/kerasformers/dino-v1-v2-v3-6a6a94f8281a2f373f70e769)
-
-# kerasformers/dinov2-small
-
-Paper: [DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193)](https://arxiv.org/abs/2304.07193) · [HF Papers](https://huggingface.co/papers/2304.07193)
-
-DINOv2 scales self-supervised ViT pretraining for strong transferable visual features without labels. These checkpoints are backbones that return patch tokens for downstream heads.
-
-For more details on the model, please go to the upstream [model card](https://huggingface.co/facebook/dinov2-small).
-
-Pure-**Keras 3** conversion of [`facebook/dinov2-small`](https://huggingface.co/facebook/dinov2-small) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
-
-This is a **self-supervised backbone** (`DinoV2Model`), not a task head.
-
-## ✨ Quick start
-
-```python
-import os
-os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
-
-from kerasformers.models.dino_v2 import DinoV2Model, DinoV2ImageProcessor
-
-# The processor resizes + ImageNet-normalizes, so build the model with
-# include_normalization=False (it would otherwise normalize a second time).
-model = DinoV2Model.from_weights(
-    "kerasformers/dinov2-small", include_normalization=False
-)
-processor = DinoV2ImageProcessor.from_weights("kerasformers/dinov2-small")
-
-pixel_values = processor("your_image.jpg")["pixel_values"]
-features = model(pixel_values, training=False)
-print(pixel_values.shape, features.shape)
-```
-
-Load any DINOv2 variant the same way with `from_weights("kerasformers/<variant>")`:
-
-| Variant | Hub | Backbone |
-|---|---|---|
-| `dinov2-small` | [`kerasformers/dinov2-small`](https://huggingface.co/kerasformers/dinov2-small) | ViT-S/14 |
-| `dinov2-base` | [`kerasformers/dinov2-base`](https://huggingface.co/kerasformers/dinov2-base) | ViT-B/14 |
-| `dinov2-large` | [`kerasformers/dinov2-large`](https://huggingface.co/kerasformers/dinov2-large) | ViT-L/14 |
-| `dinov2-giant` | [`kerasformers/dinov2-giant`](https://huggingface.co/kerasformers/dinov2-giant) | ViT-g/14 |
-
-## Tips
-
-- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
-- The processor normalizes; pair it with `include_normalization=False`. To skip it, feed raw `[0, 255]` pixels and keep the default `include_normalization=True`.
-- See [DINOv2 docs](https://imvision12.github.io/KerasFormers/dinov2/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
-- Community / upstream weights: `DinoV2Model.from_weights("hf:facebook/dinov2-small")`.
-
-## Special Thanks
-
-A huge thank you to the Facebook AI Research DINOv2 authors for creating and releasing these models.
-
-License: Apache 2.0.
+---
+pipeline_tag: image-feature-extraction
+license: apache-2.0
+base_model: facebook/dinov2-small
+library_name: zeromodels
+tags:
+- keras
+- zeromodels
+- dinov2
+- feature-extraction
+- vision
+- arxiv:2304.07193
+- pytorch
+- jax
+- tf
+---
+
+## ***See [our collection](https://huggingface.co/collections/zeromodels/dino-v1-v2-v3-6a6a94f8281a2f373f70e769) for all versions of DINOv2.***
+
+# Run DINOv2 with Keras 3: JAX, PyTorch, or TensorFlow
+
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-DINOv2-blue)](https://imvision12.github.io/ZeroModels/dinov2/) [![Collection](https://img.shields.io/badge/HF-DINOv2%20collection-yellow)](https://huggingface.co/collections/zeromodels/dino-v1-v2-v3-6a6a94f8281a2f373f70e769)
+
+# zeromodels/dinov2-small
+
+Paper: [DINOv2: Learning Robust Visual Features without Supervision (arXiv:2304.07193)](https://arxiv.org/abs/2304.07193) · [HF Papers](https://huggingface.co/papers/2304.07193)
+
+DINOv2 scales self-supervised ViT pretraining for strong transferable visual features without labels. These checkpoints are backbones that return patch tokens for downstream heads.
+
+For more details on the model, please go to the upstream [model card](https://huggingface.co/facebook/dinov2-small).
+
+Pure-**Keras 3** conversion of [`facebook/dinov2-small`](https://huggingface.co/facebook/dinov2-small) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+
+This is a **self-supervised backbone** (`DinoV2Model`), not a task head.
+
+## ✨ Quick start
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from zeromodels.models.dino_v2 import DinoV2Model, DinoV2ImageProcessor
+
+# The processor resizes + ImageNet-normalizes, so build the model with
+# include_normalization=False (it would otherwise normalize a second time).
+model = DinoV2Model.from_weights(
+    "zeromodels/dinov2-small", include_normalization=False
+)
+processor = DinoV2ImageProcessor.from_weights("zeromodels/dinov2-small")
+
+pixel_values = processor("your_image.jpg")["pixel_values"]
+features = model(pixel_values, training=False)
+print(pixel_values.shape, features.shape)
+```
+
+Load any DINOv2 variant the same way with `from_weights("zeromodels/<variant>")`:
+
+| Variant | Hub | Backbone |
+|---|---|---|
+| `dinov2-small` | [`zeromodels/dinov2-small`](https://huggingface.co/zeromodels/dinov2-small) | ViT-S/14 |
+| `dinov2-base` | [`zeromodels/dinov2-base`](https://huggingface.co/zeromodels/dinov2-base) | ViT-B/14 |
+| `dinov2-large` | [`zeromodels/dinov2-large`](https://huggingface.co/zeromodels/dinov2-large) | ViT-L/14 |
+| `dinov2-giant` | [`zeromodels/dinov2-giant`](https://huggingface.co/zeromodels/dinov2-giant) | ViT-g/14 |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
+- The processor normalizes; pair it with `include_normalization=False`. To skip it, feed raw `[0, 255]` pixels and keep the default `include_normalization=True`.
+- See [DINOv2 docs](https://imvision12.github.io/ZeroModels/dinov2/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
+- Community / upstream weights: `DinoV2Model.from_weights("hf:facebook/dinov2-small")`.
+
+## Special Thanks
+
+A huge thank you to the Facebook AI Research DINOv2 authors for creating and releasing these models.
+
+License: Apache 2.0.

kf_config.json → zm_config.json

@@ -1,28 +1,28 @@
-{
- "library_name": "kerasformers",
- "kerasformers_version": "1.2.1",
- "model_module": "kerasformers.models.dino_v2",
- "model_class": "DinoV2Model",
- "variant": "dinov2-small",
- "weights": "model.weights.h5",
- "schema_version": 2,
- "weight_dtype": "float32",
- "model_type": "dinov2",
- "vision_config": {
-  "as_backbone": false,
-  "patch_size": 14,
-  "embed_dim": 384,
-  "depth": 12,
-  "num_heads": 6,
-  "mlp_ratio": 4.0,
-  "qkv_bias": true,
-  "qk_norm": false,
-  "drop_rate": 0.0,
-  "attn_drop_rate": 0.0,
-  "layer_scale_init": 1.0,
-  "use_swiglu": false,
-  "include_normalization": true,
-  "normalization_mode": "imagenet",
-  "image_size": 224
- }
+{
+ "library_name": "zeromodels",
+ "zeromodels_version": "1.2.1",
+ "model_module": "zeromodels.models.dino_v2",
+ "model_class": "DinoV2Model",
+ "variant": "dinov2-small",
+ "weights": "model.weights.h5",
+ "schema_version": 2,
+ "weight_dtype": "float32",
+ "model_type": "dinov2",
+ "vision_config": {
+  "as_backbone": false,
+  "patch_size": 14,
+  "embed_dim": 384,
+  "depth": 12,
+  "num_heads": 6,
+  "mlp_ratio": 4.0,
+  "qkv_bias": true,
+  "qk_norm": false,
+  "drop_rate": 0.0,
+  "attn_drop_rate": 0.0,
+  "layer_scale_init": 1.0,
+  "use_swiglu": false,
+  "include_normalization": true,
+  "normalization_mode": "imagenet",
+  "image_size": 224
+ }
 }

kf_preprocessor.json → zm_preprocessor.json

@@ -1,23 +1,23 @@
-{
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.1",
-  "preprocessor_module": "kerasformers.models.dino_v2",
-  "preprocessor_class": "DinoV2ImageProcessor",
-  "variant": "dinov2-small",
-  "resize_size": 256,
-  "crop_size": 224,
-  "mean": [
-    0.48500001430511475,
-    0.4560000002384186,
-    0.4059999883174896
-  ],
-  "std": [
-    0.2290000021457672,
-    0.2240000069141388,
-    0.22499999403953552
-  ],
-  "do_center_crop": true,
-  "do_normalize": true,
-  "do_resize": true,
-  "data_format": "channels_last"
+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.1",
+  "preprocessor_module": "zeromodels.models.dino_v2",
+  "preprocessor_class": "DinoV2ImageProcessor",
+  "variant": "dinov2-small",
+  "resize_size": 256,
+  "crop_size": 224,
+  "mean": [
+    0.48500001430511475,
+    0.4560000002384186,
+    0.4059999883174896
+  ],
+  "std": [
+    0.2290000021457672,
+    0.2240000069141388,
+    0.22499999403953552
+  ],
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "data_format": "channels_last"
 }