Update app.py

app.py

@@ -2,9 +2,7 @@ import gradio as gr
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
-a = hf_hub_download(repo_id="TheBloke/WizardLM-13B-V1.2-GGML", filename="wizardlm-13b-v1.2.ggmlv3.q5_1.bin")
-
-llm = Llama((a,))
+llm = Llama(model_path= hf_hub_download(repo_id="TheBloke/WizardLM-13B-V1.2-GGML", filename="wizardlm-13b-v1.2.ggmlv3.q5_1.bin"))
 
 def generate_text(input_text):
     output = llm(f"Q: {input_text} A:", max_tokens=256, stop=["Q:", "\n"], echo=True)