Update app.py

app.py

@@ -12,10 +12,10 @@ import gradio as gr
 torch.set_num_threads(2)
 
 model = EmbeddingModel(use_quantized_onnx_model=True)
-tokenizer = AutoTokenizer.from_pretrained("lmsys/vicuna-7b-v1.5")
-llm = AutoModelForCausalLM.from_pretrained("lmsys/vicuna-7b-v1.5")
+tokenizer = AutoTokenizer.from_pretrained("GeneZC/MiniChat-3B", use_fast=False)
+llm = AutoModelForCausalLM.from_pretrained("GeneZC/MiniChat-3B")
 
-prompt_template = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: $PROMPT ASSISTANT: "
+prompt_template = "<s> [|User|] $PROMPT </s>[|Assistant|]"
 
 def fetch_links(query, max_results=5):
     with DDGS() as ddgs: