Update app.py

app.py

@@ -7,8 +7,8 @@ from gradio.themes.utils import colors, fonts, sizes
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
-hf_hub_download(repo_id="Pi3141/alpaca-lora-7B-ggml", filename="ggml-model-q4_0.bin", local_dir=".")
-llm = Llama(model_path="./ggml-model-q4_0.bin", n_threads=2)
+hf_hub_download(repo_id="Pi3141/alpaca-lora-7B-ggml", filename="ggml-model-q4_1.bin", local_dir=".")
+llm = Llama(model_path="./ggml-model-q4_1.bin")
 
 
 ins = '''Below is an instruction that describes a task. Write a response that appropriately completes the request.
@@ -113,8 +113,8 @@ with gr.Blocks(theme=seafoam, analytics_enabled=False, css=css) as demo:
     with gr.Column():
         gr.Markdown(
             """ ## Alpaca-LoRa
-            
-            is a 7B-parameter LLaMA model finetuned to follow instructions. It is trained on the Stanford Alpaca dataset and makes use of the Huggingface LLaMA implementation.
+
+            7b quantized 4bit (q4_1)
             
             Type in the box below and click the button to generate answers to your most pressing questions!