Update app.py

app.py

@@ -3,12 +3,16 @@ from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 import os
 import requests
+from llama_cpp.server.app import create_app
+from llama_cpp.server.settings import Settings
+
+
 os.system("ulimit -l unlimited")
 
 app = FastAPI()
 
 hf_hub_download("TheBloke/deepseek-coder-1.3b-base-GGUF", "deepseek-coder-1.3b-base.Q5_K_M.gguf", local_dir="./")
-model_l = Llama(model_path="./deepseek-coder-1.3b-base.Q5_K_M.gguf", n_ctx=16000, n_gpu_layers=0, n_threads=2, use_mlock=True)
+model_l = Llama(model_path="./deepseek-coder-1.3b-base.Q5_K_M.gguf", n_ctx=16192, n_gpu_layers=0, n_threads=2, use_mlock=True)
 
 
 @app.get("/check")
@@ -34,6 +38,14 @@ async def completion(request: Request):
     except:
         return {"responses": "Error!"}
 
+
+app = create_app(
+        Settings(
+            n_threads=2,  # set to number of cpu cores
+            model="./deepseek-coder-1.3b-base.Q5_K_M.gguf",
+            embedding=True
+            ))
+
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=7860)