Fix gen_kwargs, by expanding inputs

app.py

@@ -79,7 +79,7 @@ def generate(term, deps, temperature, top_p, max_new_tokens):
     inputs = tokenizer(prompt_text, return_tensors="pt").to(device)
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
     gen_kwargs = dict(
-        inputs=inputs,
+        **inputs,
         max_new_tokens=int(max_new_tokens),
         temperature=float(temperature),
         top_p=float(top_p),