Update app.py

app.py

@@ -10,7 +10,6 @@ import asyncio
 import random
 from io import BytesIO
 import requests
-import tempfile
 
 app = FastAPI()
 load_dotenv()
@@ -34,21 +33,24 @@ class ModelManager:
     def load_unified_model(self):
         model_configs = [
             {
-                "repo_id": "unsloth/Llama-3.2-3B-Instruct-GGUF",
-                "filename": "Llama-3.2-3B-Instruct-Q4_K_M.gguf",
-                "name": "Llama-3.2-3B-Instruct-GGUF"
+                "repo_id": "TheBloke/Llama-2-7B-Chat-GGUF",
+                "filename": "llama-2-7b-chat.Q4_K_M.gguf",
             },
         ]
 
         models = []
         for config in model_configs:
-            with BytesIO() as model_data: 
+            with BytesIO() as model_data:
                 download_url = f"https://huggingface.co/{config['repo_id']}/resolve/main/{config['filename']}"
-                response = requests.get(download_url, headers={"Authorization": f"Bearer {HUGGINGFACE_TOKEN}"})
-                model_data.write(response.content)
-                model_data.seek(0) 
-
-                model = Llama(model_path=" ", model_data=model_data.read(), **self.params)
+                response = requests.get(download_url, headers={"Authorization": f"Bearer {HUGGINGFACE_TOKEN}", "stream": True})
+                
+                for chunk in response.iter_content(chunk_size=1024*1024):
+                    if chunk: 
+                        model_data.write(chunk)
+                
+                model_data.seek(0)
+
+                model = Llama(model_path="", model_data=model_data.read(), **self.params)
                 models.append(model)
 
                 self.params["tokens"] = models[0].tokenize(b"Hello")