Hello

app.py

@@ -0,0 +1,20 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MODEL = "google/gemma-3-270m"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
+model = AutoModelForCausalLM.from_pretrained(MODEL)
+
+def chat(message, history):
+    inputs = tokenizer(message, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=128)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+gr.Interface(
+    fn=chat,
+    inputs=["text", "state"],
+    outputs=["text"],
+    title="Gemma 3 (270M)"
+).launch()

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+accelerate
+torch
+gradio