Add Gemma4TextGenerate text-only usage example

README.md

@@ -47,6 +47,24 @@ For model details, license, and usage terms, see Google's
 
 ## ✨ Quick start
 
+### Text-only
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from kerasformers.models.gemma4 import Gemma4TextGenerate, Gemma4Tokenizer
+
+model = Gemma4TextGenerate.from_weights("kerasformers/gemma-4-31b")
+tokenizer = Gemma4Tokenizer.from_weights("kerasformers/gemma-4-31b")
+
+inputs = tokenizer([{"role": "user", "content": "Hello, who are you?"}])
+outputs = model.generate(**inputs, max_new_tokens=64)
+print(tokenizer.decode(outputs[0]))
+```
+
+### Image + text
+
 ```python
 import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"