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-object-detection
 license: apache-2.0
 base_model: google/owlvit-base-patch32
-library_name: kerasformers
+library_name: zeromodels
 tags:
 - keras
-- kerasformers
+- zeromodels
 - owlvit
 - open-vocabulary
 - zero-shot-object-detection
@@ -16,13 +16,13 @@ tags:
 - tf
 ---
 
-## ***See [our collection](https://huggingface.co/collections/kerasformers/owl-vit-6a6a7af2bb61206cd50397ff) for all versions of OWL-ViT.***
+## ***See [our collection](https://huggingface.co/collections/zeromodels/owl-vit-6a6a7af2bb61206cd50397ff) for all versions of OWL-ViT.***
 
 # Run OWL-ViT 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-OWL--ViT-blue)](https://imvision12.github.io/KerasFormers/owlvit/) [![Collection](https://img.shields.io/badge/HF-OWL--ViT%20collection-yellow)](https://huggingface.co/collections/kerasformers/owl-vit-6a6a7af2bb61206cd50397ff)
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-OWL--ViT-blue)](https://imvision12.github.io/ZeroModels/owlvit/) [![Collection](https://img.shields.io/badge/HF-OWL--ViT%20collection-yellow)](https://huggingface.co/collections/zeromodels/owl-vit-6a6a7af2bb61206cd50397ff)
 
-# kerasformers/owlvit-base-patch32
+# zeromodels/owlvit-base-patch32
 
 Paper: [Simple Open-Vocabulary Object Detection with Vision Transformers (arXiv:2205.06230)](https://arxiv.org/abs/2205.06230) · [HF Papers](https://huggingface.co/papers/2205.06230)
 
@@ -30,7 +30,7 @@ OWL-ViT detects objects described by free text, with no fixed class list. It sta
 
 For more details on the model, please go to Google's original [model card](https://huggingface.co/google/owlvit-base-patch32).
 
-Pure-**Keras 3** conversion of [`google/owlvit-base-patch32`](https://huggingface.co/google/owlvit-base-patch32) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+Pure-**Keras 3** conversion of [`google/owlvit-base-patch32`](https://huggingface.co/google/owlvit-base-patch32) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
 
 This is an **open-vocabulary object detection** checkpoint (`OwlViTDetect`): pass free-text prompts at inference time.
 
@@ -41,15 +41,15 @@ import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 
 from PIL import Image
-from kerasformers.models.owlvit import (
+from zeromodels.models.owlvit import (
     OwlViTDetect,
     OwlViTProcessor,
     OwlViTImageProcessor,
 )
 
-model = OwlViTDetect.from_weights("kerasformers/owlvit-base-patch32")
-processor = OwlViTProcessor.from_weights("kerasformers/owlvit-base-patch32")
-image_processor = OwlViTImageProcessor.from_weights("kerasformers/owlvit-base-patch32")
+model = OwlViTDetect.from_weights("zeromodels/owlvit-base-patch32")
+processor = OwlViTProcessor.from_weights("zeromodels/owlvit-base-patch32")
+image_processor = OwlViTImageProcessor.from_weights("zeromodels/owlvit-base-patch32")
 
 image = Image.open("your_image.jpg").convert("RGB")
 prompts = ["a photo of a mug", "a photo of a knife"]
@@ -72,27 +72,27 @@ for score, name, box in zip(
     print(f"{name}: {float(score):.3f} {box}")
 ```
 
-Load any OWL-ViT / OWLv2 variant the same way with `from_weights("kerasformers/<variant>")` (use `OwlViTDetect` for this repo):
+Load any OWL-ViT / OWLv2 variant the same way with `from_weights("zeromodels/<variant>")` (use `OwlViTDetect` for this repo):
 
 | Variant | Hub | Family |
 |---|---|---|
-| `owlvit-base-patch32` | [`kerasformers/owlvit-base-patch32`](https://huggingface.co/kerasformers/owlvit-base-patch32) | OWL-ViT |
-| `owlvit-base-patch16` | [`kerasformers/owlvit-base-patch16`](https://huggingface.co/kerasformers/owlvit-base-patch16) | OWL-ViT |
-| `owlvit-large-patch14` | [`kerasformers/owlvit-large-patch14`](https://huggingface.co/kerasformers/owlvit-large-patch14) | OWL-ViT |
-| `owlv2-base-patch16` | [`kerasformers/owlv2-base-patch16`](https://huggingface.co/kerasformers/owlv2-base-patch16) | OWLv2 |
-| `owlv2-base-patch16-ensemble` | [`kerasformers/owlv2-base-patch16-ensemble`](https://huggingface.co/kerasformers/owlv2-base-patch16-ensemble) | OWLv2 |
-| `owlv2-base-patch16-finetuned` | [`kerasformers/owlv2-base-patch16-finetuned`](https://huggingface.co/kerasformers/owlv2-base-patch16-finetuned) | OWLv2 |
-| `owlv2-large-patch14` | [`kerasformers/owlv2-large-patch14`](https://huggingface.co/kerasformers/owlv2-large-patch14) | OWLv2 |
-| `owlv2-large-patch14-ensemble` | [`kerasformers/owlv2-large-patch14-ensemble`](https://huggingface.co/kerasformers/owlv2-large-patch14-ensemble) | OWLv2 |
-| `owlv2-large-patch14-finetuned` | [`kerasformers/owlv2-large-patch14-finetuned`](https://huggingface.co/kerasformers/owlv2-large-patch14-finetuned) | OWLv2 |
+| `owlvit-base-patch32` | [`zeromodels/owlvit-base-patch32`](https://huggingface.co/zeromodels/owlvit-base-patch32) | OWL-ViT |
+| `owlvit-base-patch16` | [`zeromodels/owlvit-base-patch16`](https://huggingface.co/zeromodels/owlvit-base-patch16) | OWL-ViT |
+| `owlvit-large-patch14` | [`zeromodels/owlvit-large-patch14`](https://huggingface.co/zeromodels/owlvit-large-patch14) | OWL-ViT |
+| `owlv2-base-patch16` | [`zeromodels/owlv2-base-patch16`](https://huggingface.co/zeromodels/owlv2-base-patch16) | OWLv2 |
+| `owlv2-base-patch16-ensemble` | [`zeromodels/owlv2-base-patch16-ensemble`](https://huggingface.co/zeromodels/owlv2-base-patch16-ensemble) | OWLv2 |
+| `owlv2-base-patch16-finetuned` | [`zeromodels/owlv2-base-patch16-finetuned`](https://huggingface.co/zeromodels/owlv2-base-patch16-finetuned) | OWLv2 |
+| `owlv2-large-patch14` | [`zeromodels/owlv2-large-patch14`](https://huggingface.co/zeromodels/owlv2-large-patch14) | OWLv2 |
+| `owlv2-large-patch14-ensemble` | [`zeromodels/owlv2-large-patch14-ensemble`](https://huggingface.co/zeromodels/owlv2-large-patch14-ensemble) | OWLv2 |
+| `owlv2-large-patch14-finetuned` | [`zeromodels/owlv2-large-patch14-finetuned`](https://huggingface.co/zeromodels/owlv2-large-patch14-finetuned) | OWLv2 |
 
 ## Tips
 
-- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
 - Prefer `Processor.from_weights(...)` so image size matches the variant.
 - Open-vocab thresholds are often much lower than closed-set detectors (try `0.1`).
 - OWLv2 pads to square before resize; pass the original `(height, width)` as `target_sizes` carefully (see the OWLv2 docs for the padding trap).
-- See [OWL-ViT docs](https://imvision12.github.io/KerasFormers/owlvit/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
+- See [OWL-ViT docs](https://imvision12.github.io/ZeroModels/owlvit/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
 - Community / upstream safetensors still work via the `hf:` prefix, e.g. `OwlViTDetect.from_weights("hf:google/owlvit-base-patch32")`.
 
 ## Special Thanks

kf_config.json → zm_config.json

@@ -1,29 +1,29 @@
-{
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.1",
-  "model_module": "kerasformers.models.owlvit",
-  "model_class": "OwlViTDetect",
-  "variant": "owlvit-base-patch32",
-  "weights": "model.weights.h5",
-  "schema_version": 2,
-  "weight_dtype": "float32",
-  "model_type": "owlvit",
-  "text_config": {
-    "hidden_dim": 512,
-    "intermediate_size": 2048,
-    "num_heads": 8,
-    "num_layers": 12,
-    "max_position_embeddings": 16,
-    "vocab_size": 49408
-  },
-  "vision_config": {
-    "image_size": 768,
-    "patch_size": 32,
-    "hidden_dim": 768,
-    "intermediate_size": 3072,
-    "num_layers": 12,
-    "num_heads": 12
-  },
-  "projection_dim": 512,
-  "image_size": null
+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.1",
+  "model_module": "zeromodels.models.owlvit",
+  "model_class": "OwlViTDetect",
+  "variant": "owlvit-base-patch32",
+  "weights": "model.weights.h5",
+  "schema_version": 2,
+  "weight_dtype": "float32",
+  "model_type": "owlvit",
+  "text_config": {
+    "hidden_dim": 512,
+    "intermediate_size": 2048,
+    "num_heads": 8,
+    "num_layers": 12,
+    "max_position_embeddings": 16,
+    "vocab_size": 49408
+  },
+  "vision_config": {
+    "image_size": 768,
+    "patch_size": 32,
+    "hidden_dim": 768,
+    "intermediate_size": 3072,
+    "num_layers": 12,
+    "num_heads": 12
+  },
+  "projection_dim": 512,
+  "image_size": null
 }

kf_preprocessor.json → zm_preprocessor.json

@@ -1,27 +1,27 @@
-{
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.1.3",
-  "preprocessor_module": "kerasformers.models.owlvit",
-  "preprocessor_class": "OwlViTImageProcessor",
-  "variant": "owlvit-base-patch32",
-  "size": {
-    "height": 768,
-    "width": 768
-  },
-  "resample": "bicubic",
-  "do_rescale": true,
-  "rescale_factor": 0.00392156862745098,
-  "do_normalize": true,
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "return_tensor": true,
-  "data_format": null
+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.1.3",
+  "preprocessor_module": "zeromodels.models.owlvit",
+  "preprocessor_class": "OwlViTImageProcessor",
+  "variant": "owlvit-base-patch32",
+  "size": {
+    "height": 768,
+    "width": 768
+  },
+  "resample": "bicubic",
+  "do_rescale": true,
+  "rescale_factor": 0.00392156862745098,
+  "do_normalize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "return_tensor": true,
+  "data_format": null
 }