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

README.md

@@ -4,10 +4,10 @@ license: other
 license_name: deepseek
 license_link: https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat/blob/main/LICENSE
 base_model: deepseek-ai/deepseek-vl-7b-chat
-library_name: kerasformers
+library_name: zeromodels
 tags:
 - keras
-- kerasformers
+- zeromodels
 - deepseek-vl
 - vision-language
 - image-text-to-text
@@ -17,21 +17,21 @@ tags:
 - tf
 ---
 
-## ***See [our collection](https://huggingface.co/collections/kerasformers/deepseek-vl-6a6ea961fe80d98b7c69b489) for all versions of DeepSeek-VL.***
+## ***See [our collection](https://huggingface.co/collections/zeromodels/deepseek-vl-6a6ea961fe80d98b7c69b489) for all versions of DeepSeek-VL.***
 
 # Run DeepSeek-VL 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-DeepSeek--VL--Hybrid-blue)](https://imvision12.github.io/KerasFormers/deepseek_vl_hybrid/) [![Collection](https://img.shields.io/badge/HF-DeepSeek--VL%20collection-yellow)](https://huggingface.co/collections/kerasformers/deepseek-vl-6a6ea961fe80d98b7c69b489)
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-DeepSeek--VL--Hybrid-blue)](https://imvision12.github.io/ZeroModels/deepseek_vl_hybrid/) [![Collection](https://img.shields.io/badge/HF-DeepSeek--VL%20collection-yellow)](https://huggingface.co/collections/zeromodels/deepseek-vl-6a6ea961fe80d98b7c69b489)
 
-# kerasformers/deepseek_vl_7b_chat
+# zeromodels/deepseek_vl_7b_chat
 
 Paper: [DeepSeek-VL: Towards Real-World Vision-Language Understanding (arXiv:2403.05525)](https://arxiv.org/abs/2403.05525) · [HF Papers](https://huggingface.co/papers/2403.05525)
 
-DeepSeek-VL **7B hybrid** uses a dual vision tower (SigLIP @384 + SAM-style @1024) and a 3-way aligner for finer detail and small text. Import from `kerasformers.models.deepseek_vl_hybrid` (not `deepseek_vl`).
+DeepSeek-VL **7B hybrid** uses a dual vision tower (SigLIP @384 + SAM-style @1024) and a 3-way aligner for finer detail and small text. Import from `zeromodels.models.deepseek_vl_hybrid` (not `deepseek_vl`).
 
 For more details on the model, please go to the upstream [model card](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat).
 
-Pure-**Keras 3** conversion of [`deepseek-ai/deepseek-vl-7b-chat`](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+Pure-**Keras 3** conversion of [`deepseek-ai/deepseek-vl-7b-chat`](https://huggingface.co/deepseek-ai/deepseek-vl-7b-chat) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
 
 This is a **vision-language** (chat) checkpoint (`DeepseekVLHybridConditionalGenerate`, 7B chat (SigLIP + SAM hybrid)).
 
@@ -42,13 +42,13 @@ import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 
 from PIL import Image
-from kerasformers.models.deepseek_vl_hybrid import (
+from zeromodels.models.deepseek_vl_hybrid import (
     DeepseekVLHybridConditionalGenerate,
     DeepseekVLHybridProcessor,
 )
 
-model = DeepseekVLHybridConditionalGenerate.from_weights("kerasformers/deepseek_vl_7b_chat")
-processor = DeepseekVLHybridProcessor.from_weights("kerasformers/deepseek_vl_7b_chat")
+model = DeepseekVLHybridConditionalGenerate.from_weights("zeromodels/deepseek_vl_7b_chat")
+processor = DeepseekVLHybridProcessor.from_weights("zeromodels/deepseek_vl_7b_chat")
 
 image = Image.open("your_image.jpg")
 inputs = processor(
@@ -66,21 +66,21 @@ outputs = model.generate(**inputs, max_new_tokens=64)
 print(processor.decode(outputs[0]))
 ```
 
-Load any DeepSeek-VL variant the same way with `from_weights("kerasformers/<variant>")`:
+Load any DeepSeek-VL variant the same way with `from_weights("zeromodels/<variant>")`:
 
 | Variant | Hub | Notes |
 |---|---|---|
-| `deepseek_vl_1.3b_base` | [`kerasformers/deepseek_vl_1.3b_base`](https://huggingface.co/kerasformers/deepseek_vl_1.3b_base) | 1.3B base |
-| `deepseek_vl_1.3b_chat` | [`kerasformers/deepseek_vl_1.3b_chat`](https://huggingface.co/kerasformers/deepseek_vl_1.3b_chat) | 1.3B chat |
-| `deepseek_vl_7b_base` | [`kerasformers/deepseek_vl_7b_base`](https://huggingface.co/kerasformers/deepseek_vl_7b_base) | 7B hybrid base |
-| `deepseek_vl_7b_chat` | [`kerasformers/deepseek_vl_7b_chat`](https://huggingface.co/kerasformers/deepseek_vl_7b_chat) | 7B hybrid chat |
+| `deepseek_vl_1.3b_base` | [`zeromodels/deepseek_vl_1.3b_base`](https://huggingface.co/zeromodels/deepseek_vl_1.3b_base) | 1.3B base |
+| `deepseek_vl_1.3b_chat` | [`zeromodels/deepseek_vl_1.3b_chat`](https://huggingface.co/zeromodels/deepseek_vl_1.3b_chat) | 1.3B chat |
+| `deepseek_vl_7b_base` | [`zeromodels/deepseek_vl_7b_base`](https://huggingface.co/zeromodels/deepseek_vl_7b_base) | 7B hybrid base |
+| `deepseek_vl_7b_chat` | [`zeromodels/deepseek_vl_7b_chat`](https://huggingface.co/zeromodels/deepseek_vl_7b_chat) | 7B hybrid chat |
 
 ## Tips
 
-- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
 - Prefer `Processor.from_weights(...)` so vision + tokenizer match.
 - 7B hybrid is a **different package** than 1.3B; do not mix imports.
-- See [docs](https://imvision12.github.io/KerasFormers/deepseek_vl_hybrid/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
+- See [docs](https://imvision12.github.io/ZeroModels/deepseek_vl_hybrid/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
 - Community / upstream safetensors still work via the `hf:` prefix, e.g. `DeepseekVLHybridConditionalGenerate.from_weights("hf:deepseek-ai/deepseek-vl-7b-chat")`.
 
 ## Special Thanks

kf_config.json → zm_config.json

@@ -1,7 +1,7 @@
 {
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.1",
-  "model_module": "kerasformers.models.deepseek_vl_hybrid",
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.1",
+  "model_module": "zeromodels.models.deepseek_vl_hybrid",
   "model_class": "DeepseekVLHybridModel",
   "variant": "deepseek_vl_7b_chat",
   "weights": "model.weights.json",

kf_preprocessor.json → zm_preprocessor.json

@@ -1,41 +1,41 @@
-{
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.1.3",
-  "preprocessor_module": "kerasformers.models.deepseek_vl_hybrid",
-  "preprocessor_class": "DeepseekVLHybridImageProcessor",
-  "variant": "deepseek_vl_7b_chat",
-  "size": 384,
-  "high_res_size": 1024,
-  "min_size": 14,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "high_res_image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "high_res_image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "background_color": [
-    127,
-    127,
-    127
-  ],
-  "high_res_background_color": [
-    122,
-    116,
-    104
-  ],
-  "data_format": null
+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.1.3",
+  "preprocessor_module": "zeromodels.models.deepseek_vl_hybrid",
+  "preprocessor_class": "DeepseekVLHybridImageProcessor",
+  "variant": "deepseek_vl_7b_chat",
+  "size": 384,
+  "high_res_size": 1024,
+  "min_size": 14,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "high_res_image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "high_res_image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "background_color": [
+    127,
+    127,
+    127
+  ],
+  "high_res_background_color": [
+    122,
+    116,
+    104
+  ],
+  "data_format": null
 }