Update app.py

app.py

@@ -16,12 +16,12 @@ ACTIONS = [
     "chat_only"
 ]
 
-# Load model and tokenizer (you'll fine-tune this on your specific task)
-model_name = "models/microsoft/deberta-v3-small"  # Starting point, you'll need to fine-tune
+# Load model and tokenizer - CORRECTED MODEL NAME
+model_name = "microsoft/deberta-v3-small"  # Correct format for model name
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=len(ACTIONS))
 
-# This function will need to be trained/fine-tuned with your data
+# This function will need to be trained with your data
 def predict_action(text):
     inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
     outputs = model(**inputs)
@@ -41,23 +41,12 @@ def process_text(text):
     return result["action"], result["confidence"], result["all_actions"]
 
 # Define the Gradio interface
-with gr.Blocks() as demo:
-    gr.Markdown("# Minecraft Action Predictor")
-    with gr.Row():
-        text_input = gr.Textbox(label="Character text")
-        action_output = gr.Textbox(label="Predicted action")
-    with gr.Row():
-        confidence_output = gr.Number(label="Confidence")
-        all_actions_output = gr.JSON(label="All action probabilities")
-    
-    text_input.change(process_text, inputs=text_input, outputs=[action_output, confidence_output, all_actions_output])
-    
-    gr.Interface(
-        fn=predict_action,
-        inputs=gr.Textbox(label="Character text"),
-        outputs=gr.JSON(label="Result"),
-        title="Minecraft Action Predictor API",
-        description="Predicts the best action based on character text"
-    )
+demo = gr.Interface(
+    fn=predict_action,
+    inputs=gr.Textbox(label="Character text"),
+    outputs=gr.JSON(label="Result"),
+    title="Minecraft Action Predictor",
+    description="Predicts the best action based on character text"
+)
 
 demo.launch()