Update app.py

app.py

@@ -42,7 +42,7 @@ def generate_responses(prompt, history):
     #already has special tokens
     inputs = tokenizer.encode(wrapped_prompt, add_special_tokens=False, return_tensors="pt").to("cuda")
     def standard_task():
-        return model1.generate(**inputs, max_length=2048, temperature=0.7)
+        return model1.generate(inputs, max_length=2048, temperature=0.7)
 
     # Custom sampler task: loop over generator and collect outputs in a list
     async def custom_sampler_task():