1232

app.py

@@ -8,17 +8,15 @@ MODEL = "google/gemma-3-270m"
 tokenizer = AutoTokenizer.from_pretrained(MODEL, token=HF_TOKEN)
 model = AutoModelForCausalLM.from_pretrained(MODEL, token=HF_TOKEN)
 
-def chat(message, history):
+def chat(message):
     inputs = tokenizer(message, return_tensors="pt")
     outputs = model.generate(**inputs, max_new_tokens=128)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-    history = history + [(message, response)]
-    return response, history
+    return response
 
 gr.Interface(
     fn=chat,
-    inputs=["text", "state"],
-    outputs=["text", "state"],  # <-- required
+    inputs="text",
+    outputs="text",
     title="Gemma 3 (270M)"
 ).launch()