updated inference function

app.py

@@ -35,26 +35,21 @@ def create_prompt_with_chat_format(messages, bos="<s>", eos="</s>", add_bos=True
     formatted_text = bos + formatted_text if add_bos else formatted_text
     return formatted_text
 
+def inference(input_prompt, model, tokenizer):
+    input_prompt = create_prompt_with_chat_format([{"role": "user", "content": input_prompt}], add_bos=False)
 
-def inference(input_prompts, model, tokenizer):
-    input_prompts = [
-        create_prompt_with_chat_format([{"role": "user", "content": input_prompt}], add_bos=False)
-        for input_prompt in input_prompts
-    ]
-
-    encodings = tokenizer(input_prompts, padding=True, return_tensors="pt")
+    encodings = tokenizer(input_prompt, padding=True, return_tensors="pt")
     encodings = encodings.to(device)
 
     with torch.inference_mode():  # Add missing import statement for torch.inference_mode()
         outputs = model.generate(encodings.input_ids, do_sample=False, max_new_tokens=250)
 
-    output_texts = tokenizer.batch_decode(outputs.detach(), skip_special_tokens=True)
+    output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    input_prompt = tokenizer.decode(tokenizer.encode(input_prompt), skip_special_tokens=True)
+    output_text = output_text[len(input_prompt):]
 
-    input_prompts = [
-        tokenizer.decode(tokenizer.encode(input_prompt), skip_special_tokens=True) for input_prompt in input_prompts
-    ]
-    output_texts = [output_text[len(input_prompt) :] for input_prompt, output_text in zip(input_prompts, output_texts)]
-    return output_texts
+    return output_text
 
 
 def chat_interface(message,history):