Update app.py

app.py

@@ -51,7 +51,6 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
     
 
     generate_kwargs = dict(
-        input_ids=input_ids, 
         max_length=2500, 
         max_new_tokens=max_new_tokens,
         do_sample=True,
@@ -61,7 +60,7 @@ def stream_chat(message: str, history: list, temperature: float, max_new_tokens:
     )
 
     with torch.no_grad():
-        outputs = model.generate(**generate_kwargs)
+        outputs = model.generate(**inputs, **generate_kwargs)
         outputs = outputs[:, inputs['input_ids'].shape[1]:]
         results = tokenizer.decode(outputs[0], skip_special_tokens=True)
         return results