Update README.md

README.md

@@ -1,10 +1,76 @@
 ---
-title: README
-emoji: 👁
-colorFrom: gray
-colorTo: red
-sdk: static
-pinned: false
+tags:
+- keras
+- kerasformers
+- jax
+- pytorch
+- tensorflow
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+<div align="center">
+
+# KerasFormers
+
+**Pretrained transformers in pure Keras 3. One implementation, runs on JAX, PyTorch, and TensorFlow.**
+
+[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-181717?logo=github)](https://github.com/IMvision12/KerasFormers)
+[![Docs](https://img.shields.io/badge/Docs-Website-4a9eff)](https://imvision12.github.io/KerasFormers/)
+[![Keras 3](https://img.shields.io/badge/Built%20with-Keras%203-d00000?logo=keras)](https://keras.io)
+
+</div>
+
+---
+
+This organization hosts **pre-converted Keras 3 weights** for
+[kerasformers](https://github.com/IMvision12/KerasFormers). Each repo holds the converted
+model plus its tokenizer and config files, so you download once and load directly, no
+on-the-fly conversion, no `transformers` or `torch` runtime on the model path.
+
+Every model is a pure-Keras port that runs **unchanged on all three backends**. Set
+`KERAS_BACKEND` before importing Keras and the same code runs on JAX, PyTorch, or
+TensorFlow.
+
+## Quick start
+
+```bash
+pip install kerasformers
+```
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"   # or "jax" / "tensorflow"
+
+from kerasformers.models.qwen3 import Qwen3Generate, Qwen3Tokenizer
+
+model = Qwen3Generate.from_weights("qwen3-8b")
+tokenizer = Qwen3Tokenizer.from_weights("qwen3-8b")
+
+inputs = tokenizer("The capital of France is")
+output = model.generate(**inputs, max_new_tokens=20)
+print(tokenizer.decode(output[0]))
+```
+
+## What's here
+
+Language, vision, audio, and multimodal models, all pure Keras 3:
+
+| Type | Examples |
+|---|---|
+| **Text** | Qwen, Llama, Gemma, Mistral, Mixtral, DeepSeek, GLM, GPT |
+| **Vision** | ViT, DINOv3, DETR, SegFormer, SAM, Depth Anything |
+| **Audio** | Whisper, Moonshine, Speech2Text, Granite Speech |
+| **Multimodal** | Qwen-VL, InternVL, CLIP, SigLIP, Gemma 3 |
+
+Browse the models on this page, or see the full catalog in the
+[documentation](https://imvision12.github.io/KerasFormers/).
+
+## Links
+
+- **Library**: [github.com/IMvision12/KerasFormers](https://github.com/IMvision12/KerasFormers)
+- **Documentation**: [imvision12.github.io/KerasFormers](https://imvision12.github.io/KerasFormers/)
+
+## License
+
+Each model repo carries the license of its source model. The weights here are format
+conversions of the original checkpoints; using them requires complying with the upstream
+license (Apache 2.0, Llama Community License, Gemma Terms, and so on).