Update app.py

app.py

@@ -108,7 +108,7 @@ def run_llm(
     )
     if VERBOSE:
         logging.info(LOG_RESPONSE.format(resp=resp))
-    return resp
+    return resp.text  # Access the text attribute of the response
 
 
 def generate(
@@ -130,19 +130,16 @@ def generate(
     if VERBOSE:
         logging.info(LOG_PROMPT.format(content=content))
     client = InferenceClient(model=MODEL_NAME, token=API_KEY)
-    stream = client.text_generation(
+    response = client.text_generation(
         content,
-        stream=True,
-        details=True,
-        return_full_text=False,
+        max_new_tokens=max_new_tokens,
         temperature=temperature,
         top_p=top_p,
         repetition_penalty=repetition_penalty,
-        max_new_tokens=max_new_tokens,
     )
-    response = "".join(chunk.text for chunk in stream)
-    return response
-
+    if VERBOSE:
+        logging.info(LOG_RESPONSE.format(resp=response))
+    return response.text
 
 def main():
     """Main function to launch the Gradio interface."""