Standardize README to the kerasformers structure

README.md

@@ -25,19 +25,25 @@ tags:
 - tf
 ---
 
-# gemma-3n-e2b
+*See [our collection](https://huggingface.co/kerasformers) for all Gemma 3n sizes and variants.*
 
-Pure-[Keras 3](https://keras.io/keras_3/) port of `gemma-3n-e2b`, a vision-language model in [kerasformers](https://github.com/IMvision12/KerasFormers) (backend-agnostic: JAX / TensorFlow / PyTorch). The repo carries `kf_config.json` + Keras weights; load with `from_weights("kerasformers/gemma-3n-e2b")`.
+# Run Gemma 3n with Keras 3: JAX, PyTorch, or TensorFlow
 
-## Installation
+[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-181717?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-Gemma_3n-1f6feb)](https://imvision12.github.io/KerasFormers/gemma3n/) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Gemma_3n-ffd21e?logo=huggingface&logoColor=black)](https://huggingface.co/kerasformers)
 
-```bash
-pip install kerasformers
-```
+# kerasformers/gemma-3n-e2b
+
+Pure-**Keras 3** conversion of [`google/gemma-3n-E2B`](https://huggingface.co/google/gemma-3n-E2B) for
+[kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on
+**TensorFlow / Torch / JAX**. This is a base (pretrained) checkpoint, served here as **image + audio + text -> text** via `Gemma3nConditionalGenerate`; weights are
+stored in **bfloat16**.
+
+For model details, license, and usage terms, see Google's
+[model card](https://huggingface.co/google/gemma-3n-E2B).
 
-## Usage
+## ✨ Quick start
 
-### Text generation
+### Text-only
 
 ```python
 import os
@@ -53,7 +59,7 @@ outputs = model.generate(**inputs, max_new_tokens=64)
 print(tokenizer.decode(outputs[0]))
 ```
 
-### Image + text generation
+### Image + audio + text
 
 ```python
 from kerasformers.models.gemma3n import Gemma3nConditionalGenerate, Gemma3nProcessor
@@ -72,6 +78,26 @@ outputs = model.generate(**inputs, max_new_tokens=64)
 print(processor.decode(outputs[0]))
 ```
 
----
+Load any Gemma 3n variant the same way with `from_weights("kerasformers/<variant>")`:
+
+| Variant | Hub |
+| --- | --- |
+| `gemma-3n-e2b` | [kerasformers/gemma-3n-e2b](https://huggingface.co/kerasformers/gemma-3n-e2b) |
+| `gemma-3n-e2b-it` | [kerasformers/gemma-3n-e2b-it](https://huggingface.co/kerasformers/gemma-3n-e2b-it) |
+| `gemma-3n-e4b` | [kerasformers/gemma-3n-e4b](https://huggingface.co/kerasformers/gemma-3n-e4b) |
+| `gemma-3n-e4b-it` | [kerasformers/gemma-3n-e4b-it](https://huggingface.co/kerasformers/gemma-3n-e4b-it) |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- Loads in **bfloat16** by default. Pass `load_dtype="float32"` for full precision,
+  or `quantization="int8"` to shrink further.
+- See the [Gemma 3n docs](https://imvision12.github.io/KerasFormers/gemma3n/).
+- Community / upstream weights still work via the `hf:` prefix:
+  `Gemma3nConditionalGenerate.from_weights("hf:google/gemma-3n-E2B")`.
+
+## Special Thanks
+
+A huge thank you to the Google Gemma authors for creating and releasing these models.
 
-Generated with kerasformers. See the [documentation](https://github.com/IMvision12/KerasFormers) for the full API.
+License: Gemma (gated). Accept the license on the upstream Hub card before downloading.