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

README.md

@@ -2,10 +2,10 @@
 pipeline_tag: zero-shot-image-classification
 license: apache-2.0
 base_model: google/tipsv2-so400m14
-library_name: kerasformers
+library_name: zeromodels
 tags:
 - keras
-- kerasformers
+- zeromodels
 - tipsv2
 - zero-shot-image-classification
 - vision
@@ -15,13 +15,13 @@ tags:
 - tf
 ---
 
-## ***See [our collection](https://huggingface.co/collections/kerasformers/tipsv2-6a8a3f36af77204954a49fb4) for all versions of TIPSv2.***
+## ***See [our collection](https://huggingface.co/collections/zeromodels/tipsv2-6a8a3f36af77204954a49fb4) for all versions of TIPSv2.***
 
 # Run TIPSv2 with Keras 3: JAX, PyTorch, or TensorFlow
 
-[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Collection](https://img.shields.io/badge/HF-TIPSv2%20collection-yellow)](https://huggingface.co/collections/kerasformers/tipsv2-6a8a3f36af77204954a49fb4)
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Collection](https://img.shields.io/badge/HF-TIPSv2%20collection-yellow)](https://huggingface.co/collections/zeromodels/tipsv2-6a8a3f36af77204954a49fb4)
 
-# kerasformers/tipsv2-so400m14
+# zeromodels/tipsv2-so400m14
 
 Paper: [TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment (arXiv:2604.12012)](https://huggingface.co/papers/2604.12012)
 
@@ -29,7 +29,7 @@ TIPSv2 (Google DeepMind) is a CLIP/SigLIP-style dual encoder: a DINOv2-style ViT
 
 For more details on the model, please go to the upstream [model card](https://huggingface.co/google/tipsv2-so400m14).
 
-Pure-**Keras 3** conversion of [`google/tipsv2-so400m14`](https://huggingface.co/google/tipsv2-so400m14) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**. The full model and both towers load from this single repo.
+Pure-**Keras 3** conversion of [`google/tipsv2-so400m14`](https://huggingface.co/google/tipsv2-so400m14) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**. The full model and both towers load from this single repo.
 
 ## ✨ Quick start (zero-shot)
 
@@ -40,10 +40,10 @@ os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 from PIL import Image
 import numpy as np
 import keras
-from kerasformers.models.tipsv2 import Tipsv2Model, Tipsv2Processor
+from zeromodels.models.tipsv2 import Tipsv2Model, Tipsv2Processor
 
-model = Tipsv2Model.from_weights("kerasformers/tipsv2-so400m14")
-processor = Tipsv2Processor.from_weights("kerasformers/tipsv2-so400m14")
+model = Tipsv2Model.from_weights("zeromodels/tipsv2-so400m14")
+processor = Tipsv2Processor.from_weights("zeromodels/tipsv2-so400m14")
 
 image = Image.open("your_image.jpg").convert("RGB")
 texts = ["a photo of a cat", "a photo of a dog", "a photo of a car"]
@@ -56,23 +56,23 @@ print(keras.ops.convert_to_numpy(probs)[0])
 Towers only:
 
 ```python
-from kerasformers.models.tipsv2 import Tipsv2VisionModel, Tipsv2TextModel
-vision = Tipsv2VisionModel.from_weights("kerasformers/tipsv2-so400m14")
-text = Tipsv2TextModel.from_weights("kerasformers/tipsv2-so400m14")
+from zeromodels.models.tipsv2 import Tipsv2VisionModel, Tipsv2TextModel
+vision = Tipsv2VisionModel.from_weights("zeromodels/tipsv2-so400m14")
+text = Tipsv2TextModel.from_weights("zeromodels/tipsv2-so400m14")
 ```
 
-All TIPSv2 variants load the same way with `from_weights("kerasformers/<variant>")`:
+All TIPSv2 variants load the same way with `from_weights("zeromodels/<variant>")`:
 
 | Variant | Hub |
 |---|---|
-| `tipsv2-b14` | [`kerasformers/tipsv2-b14`](https://huggingface.co/kerasformers/tipsv2-b14) |
-| `tipsv2-l14` | [`kerasformers/tipsv2-l14`](https://huggingface.co/kerasformers/tipsv2-l14) |
-| `tipsv2-so400m14` | [`kerasformers/tipsv2-so400m14`](https://huggingface.co/kerasformers/tipsv2-so400m14) |
-| `tipsv2-g14` | [`kerasformers/tipsv2-g14`](https://huggingface.co/kerasformers/tipsv2-g14) |
+| `tipsv2-b14` | [`zeromodels/tipsv2-b14`](https://huggingface.co/zeromodels/tipsv2-b14) |
+| `tipsv2-l14` | [`zeromodels/tipsv2-l14`](https://huggingface.co/zeromodels/tipsv2-l14) |
+| `tipsv2-so400m14` | [`zeromodels/tipsv2-so400m14`](https://huggingface.co/zeromodels/tipsv2-so400m14) |
+| `tipsv2-g14` | [`zeromodels/tipsv2-g14`](https://huggingface.co/zeromodels/tipsv2-g14) |
 
 ## Tips
 
-- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
 - The image processor rescales to `[0, 1]` (no mean/std normalization); input resolution is 448.
 - Upstream checkpoints: `Tipsv2Model.from_weights("hf:google/tipsv2-so400m14")`.
 

kf_config.json → zm_config.json

@@ -1,7 +1,7 @@
 {
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.5",
-  "model_module": "kerasformers.models.tipsv2",
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.5",
+  "model_module": "zeromodels.models.tipsv2",
   "model_class": "Tipsv2Model",
   "variant": "tipsv2-so400m14",
   "weights": "model.weights.h5",

kf_preprocessor.json → zm_preprocessor.json

@@ -1,7 +1,7 @@
 {
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.5",
-  "preprocessor_module": "kerasformers.models.tipsv2",
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.5",
+  "preprocessor_module": "zeromodels.models.tipsv2",
   "preprocessor_class": "Tipsv2ImageProcessor",
   "variant": "tipsv2-so400m14",
   "image_resolution": 448,