Update app.py

app.py

@@ -4,7 +4,7 @@ import torch
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, TextIteratorStreamer
 
-model_id = "declare-lab/flan-alpaca-large"
+model_id = "pszemraj/flan-t5-large-instruct-dolly_hhrlhf"
 torch_device = "cuda" if torch.cuda.is_available() else "cpu"
 print("Running on device:", torch_device)
 print("CPU threads:", torch.get_num_threads())
@@ -17,7 +17,7 @@ else:
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 
-def run_generation(user_text, top_p, temperature, top_k, max_new_tokens):
+def run_generation(user_text, top_p, temperature, top_k, max_new_tokens, use_generation_config=False):
     # Get the model and tokenizer, and tokenize the user text.
     model_inputs = tokenizer([user_text], return_tensors="pt").to(torch_device)