added model download

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import spaces
 import torch
+from huggingface_hub import hf_hub_download
 
 zero = torch.Tensor([0]).cuda()
 print(zero.device) # <-- 'cpu' 🤔
@@ -10,6 +11,13 @@ def greet(n):
     print(zero.device) # <-- 'cuda:0' 🤗
     return f"Hello {zero + n} Tensor"
 
+def download_model():
+
+REPO_ID = "TheBloke/Llama-2-7B-GGUF"
+FILENAME = "llama-2-7b.Q5_K_S.gguf"
+
+hf_hub_download(repo_id=REPO_ID, filename=FILENAME)
+
 def load_model():
     from llama_cpp import Llama, LlamaGrammar
     model_url="https://huggingface.co/TheBloke/Llama-2-7B-GGUF/resolve/main/llama-2-7b.Q5_K_S.gguf"
@@ -48,7 +56,7 @@ def load_model():
         print(output['choices'][0]['text'])
         print()
 
-
+download_model()
 load_model()
 demo = gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text())
 demo.launch(share=False)

requirements.txt

@@ -1 +1,2 @@
-llama-cpp-python
+llama-cpp-python
+gradio