download llama

Dockerfile

@@ -18,6 +18,8 @@ RUN pip install accelerate
 
 # Install hugging face hub to download llama2 model
 RUN pip install --upgrade huggingface_hub
+RUN huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+
 
 RUN CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install 'llama-cpp-python[server]' --upgrade --force-reinstall --no-cache-dir 
 # Install requirements.txt 

question_paper.py

@@ -10,16 +10,11 @@ from llama_cpp import Llama
 
 from huggingface_hub import hf_hub_download
 
-# Load the model
-
-hf_hub_download(repo_id="bevangelista/Llama-2-7b-chat-hf-GGUF-Q4_K_M", filename="Llama-2-7b-chat-hf-GGUF-Q4_K_M.gguf")
-
-
 app = FastAPI()
 @app.get("/")
 def llama():
     llm = Llama(
-      model_path="./Llama-2-7b-chat-hf-GGUF-Q4_K_M.gguf",
+      model_path="./llama-2-7b.Q4_K_M.gguf",
       # n_gpu_layers=-1, # Uncomment to use GPU acceleration
       # seed=1337, # Uncomment to set a specific seed
       # n_ctx=2048, # Uncomment to increase the context window