789456

app.py

@@ -5,18 +5,20 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 HF_TOKEN = os.environ.get("HF_TOKEN")
 MODEL = "google/gemma-3-270m"
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL, use_auth_token=HF_TOKEN)
-model = AutoModelForCausalLM.from_pretrained(MODEL, use_auth_token=HF_TOKEN)
+tokenizer = AutoTokenizer.from_pretrained(MODEL, token=HF_TOKEN)
+model = AutoModelForCausalLM.from_pretrained(MODEL, token=HF_TOKEN)
 
 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
+
+    history = history + [(message, response)]
+    return response, history
 
 gr.Interface(
     fn=chat,
     inputs=["text", "state"],
-    outputs=["text"],
+    outputs=["text", "state"],  # <-- required
     title="Gemma 3 (270M)"
 ).launch()