Update app.py

app.py

@@ -8,8 +8,8 @@ torch.set_num_threads(2)
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
 # Loading the tokenizer and model from Hugging Face's model hub.
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", use_auth_token=HF_TOKEN)
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", use_auth_token=HF_TOKEN)
+tokenizer = AutoTokenizer.from_pretrained("oofnan/stegBot2", use_auth_token=HF_TOKEN)
+model = AutoModelForCausalLM.from_pretrained("oofnan/stegBot2", use_auth_token=HF_TOKEN)
 
 def count_tokens(text):
     return len(tokenizer.tokenize(text))
@@ -17,7 +17,7 @@ def count_tokens(text):
 # Function to generate model predictions.
 def predict(message, history):
 
-    formatted_prompt = f"<start_of_turn>user\n{message}<end_of_turn>\n<start_of_turn>model\n"
+    formatted_prompt = f"<start_of_turn>user\nYou are a helpful assistant that provides answers to user questions;{message}<end_of_turn>\n<start_of_turn>model\n"
     model_inputs = tokenizer(formatted_prompt, return_tensors="pt")
     
     streamer = TextIteratorStreamer(tokenizer, timeout=120., skip_prompt=True, skip_special_tokens=True)