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

README.md

@@ -2,12 +2,12 @@
 pipeline_tag: image-text-to-text
 license: apache-2.0
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
-library_name: kerasformers
+library_name: zeromodels
 language:
 - en
 tags:
 - keras
-- kerasformers
+- zeromodels
 - qwen2_5_vl
 - qwen2.5-vl
 - multimodal
@@ -18,15 +18,15 @@ tags:
 - tf
 ---
 
-*See [our collection](https://huggingface.co/collections/kerasformers/qwen25-vl-6a7cc9f463d6956b6c3ba911) for all Qwen2.5-VL sizes.*
+*See [our collection](https://huggingface.co/collections/zeromodels/qwen25-vl-6a7cc9f463d6956b6c3ba911) for all Qwen2.5-VL sizes.*
 
 # Run Qwen2.5-VL with Keras 3: JAX, PyTorch, or TensorFlow
 
-[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-181717?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-Qwen2.5--VL-1f6feb)](https://imvision12.github.io/KerasFormers/qwen2_5_vl/) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Qwen2.5--VL-ffd21e?logo=huggingface&logoColor=black)](https://huggingface.co/collections/kerasformers/qwen25-vl-6a7cc9f463d6956b6c3ba911)
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-181717?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-Qwen2.5--VL-1f6feb)](https://imvision12.github.io/ZeroModels/qwen2_5_vl/) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Qwen2.5--VL-ffd21e?logo=huggingface&logoColor=black)](https://huggingface.co/collections/zeromodels/qwen25-vl-6a7cc9f463d6956b6c3ba911)
 
-# kerasformers/qwen2.5-vl-7b-instruct
+# zeromodels/qwen2.5-vl-7b-instruct
 
-Pure-**Keras 3** conversion of [`Qwen/Qwen2.5-VL-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**. This is the **7B** variant, served here as **image + text -> text** via `Qwen2_5VLProcessor`; weights are stored in **bfloat16**.
+Pure-**Keras 3** conversion of [`Qwen/Qwen2.5-VL-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**. This is the **7B** variant, served here as **image + text -> text** via `Qwen2_5VLProcessor`; weights are stored in **bfloat16**.
 
 For model details, license, and usage terms, see the upstream [model card](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct).
 
@@ -44,10 +44,10 @@ Paper: [Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities
 import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 
-from kerasformers.models.qwen2_5_vl import Qwen2_5VLTextGenerate, Qwen2_5VLProcessor
+from zeromodels.models.qwen2_5_vl import Qwen2_5VLTextGenerate, Qwen2_5VLProcessor
 
-model = Qwen2_5VLTextGenerate.from_weights("kerasformers/qwen2.5-vl-7b-instruct")
-processor = Qwen2_5VLProcessor.from_weights("kerasformers/qwen2.5-vl-7b-instruct")
+model = Qwen2_5VLTextGenerate.from_weights("zeromodels/qwen2.5-vl-7b-instruct")
+processor = Qwen2_5VLProcessor.from_weights("zeromodels/qwen2.5-vl-7b-instruct")
 
 inputs = processor(conversation=[
     {"role": "user", "content": [{"type": "text", "text": "Hello, who are you?"}]}
@@ -63,10 +63,10 @@ import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 
 from PIL import Image
-from kerasformers.models.qwen2_5_vl import Qwen2_5VLConditionalGenerate, Qwen2_5VLProcessor
+from zeromodels.models.qwen2_5_vl import Qwen2_5VLConditionalGenerate, Qwen2_5VLProcessor
 
-model = Qwen2_5VLConditionalGenerate.from_weights("kerasformers/qwen2.5-vl-7b-instruct")
-processor = Qwen2_5VLProcessor.from_weights("kerasformers/qwen2.5-vl-7b-instruct")
+model = Qwen2_5VLConditionalGenerate.from_weights("zeromodels/qwen2.5-vl-7b-instruct")
+processor = Qwen2_5VLProcessor.from_weights("zeromodels/qwen2.5-vl-7b-instruct")
 
 inputs = processor(conversation=[
     {"role": "user", "content": [
@@ -78,14 +78,14 @@ outputs = model.generate(**inputs, max_new_tokens=64)
 print(processor.decode(outputs[0]))
 ```
 
-Load any Qwen2.5-VL variant the same way with `from_weights("kerasformers/<variant>")`:
+Load any Qwen2.5-VL variant the same way with `from_weights("zeromodels/<variant>")`:
 
 | Variant | Hub |
 | --- | --- |
-| `qwen2.5-vl-3b-instruct` | [kerasformers/qwen2.5-vl-3b-instruct](https://huggingface.co/kerasformers/qwen2.5-vl-3b-instruct) |
-| `qwen2.5-vl-7b-instruct` | [kerasformers/qwen2.5-vl-7b-instruct](https://huggingface.co/kerasformers/qwen2.5-vl-7b-instruct) |
-| `qwen2.5-vl-32b-instruct` | [kerasformers/qwen2.5-vl-32b-instruct](https://huggingface.co/kerasformers/qwen2.5-vl-32b-instruct) |
-| `qwen2.5-vl-72b-instruct` | [kerasformers/qwen2.5-vl-72b-instruct](https://huggingface.co/kerasformers/qwen2.5-vl-72b-instruct) |
+| `qwen2.5-vl-3b-instruct` | [zeromodels/qwen2.5-vl-3b-instruct](https://huggingface.co/zeromodels/qwen2.5-vl-3b-instruct) |
+| `qwen2.5-vl-7b-instruct` | [zeromodels/qwen2.5-vl-7b-instruct](https://huggingface.co/zeromodels/qwen2.5-vl-7b-instruct) |
+| `qwen2.5-vl-32b-instruct` | [zeromodels/qwen2.5-vl-32b-instruct](https://huggingface.co/zeromodels/qwen2.5-vl-32b-instruct) |
+| `qwen2.5-vl-72b-instruct` | [zeromodels/qwen2.5-vl-72b-instruct](https://huggingface.co/zeromodels/qwen2.5-vl-72b-instruct) |
 
 ## Special Thanks
 

kf_config.json → zm_config.json

@@ -1,7 +1,7 @@
 {
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.2",
-  "model_module": "kerasformers.models.qwen2_5_vl",
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.2",
+  "model_module": "zeromodels.models.qwen2_5_vl",
   "model_class": "Qwen2_5VLConditionalGenerate",
   "variant": "qwen2.5-vl-7b-instruct",
   "weights": "model.weights.json",

kf_preprocessor.json → zm_preprocessor.json

@@ -1,22 +1,22 @@
-{
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.2",
-  "preprocessor_module": "kerasformers.models.qwen2_vl",
-  "preprocessor_class": "Qwen2VLImageProcessor",
-  "variant": "qwen2.5-vl-7b-instruct",
-  "patch_size": 14,
-  "spatial_merge_size": 2,
-  "temporal_patch_size": 2,
-  "min_pixels": 3136,
-  "max_pixels": 1003520,
-  "image_mean": [
-    0.48145467042922974,
-    0.45782750844955444,
-    0.40821072459220886
-  ],
-  "image_std": [
-    0.2686295509338379,
-    0.2613025903701782,
-    0.27577710151672363
-  ]
+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.2",
+  "preprocessor_module": "zeromodels.models.qwen2_vl",
+  "preprocessor_class": "Qwen2VLImageProcessor",
+  "variant": "qwen2.5-vl-7b-instruct",
+  "patch_size": 14,
+  "spatial_merge_size": 2,
+  "temporal_patch_size": 2,
+  "min_pixels": 3136,
+  "max_pixels": 1003520,
+  "image_mean": [
+    0.48145467042922974,
+    0.45782750844955444,
+    0.40821072459220886
+  ],
+  "image_std": [
+    0.2686295509338379,
+    0.2613025903701782,
+    0.27577710151672363
+  ]
 }