Update app.py

app.py

@@ -28,6 +28,8 @@ def generate(your_prompt, task_prefix, max_new_tokens, repetition_penalty, tempe
 
     model.to(dtype)
 
+    repetition_penalty = float(repetition_penalty)
+
     input_text = f"{task_prefix}: {your_prompt}"
     input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(device)
         
@@ -51,7 +53,7 @@ task_prefix = gr.Textbox(label="Task Prefix", info="The prompt prefix for how th
 
 max_new_tokens = gr.Slider(value=512, minimum=250, maximum=512, step=1, label="Max New Tokens", info="The maximum numbers of new tokens, controls how long is the output")
     
-repetition_penalty = gr.Slider(value=1.2, minimum=0, maximum=2.0, step=0.05, precision=2, label="Repetition Penalty", info="Penalize repeated tokens, making the AI repeat less itself")
+repetition_penalty = gr.Slider(value=1.2, minimum=0, maximum=2.0, step=0.05, label="Repetition Penalty", info="Penalize repeated tokens, making the AI repeat less itself")
 
 temperature = gr.Slider(value=0.7, minimum=0, maximum=1, step=0.05, label="Temperature", info="Higher values produce more diverse outputs")