app.py

%cd /content
!apt-get -y install -qq aria2

!git clone -b V20231127 https://github.com/Troyanovsky/text-generation-webui
%cd /content/text-generation-webui
!pip install -r requirements.txt
!pip install -U gradio==3.50.2

!pip uninstall -y llama-cpp-python
!CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python --no-cache-dir

!pip uninstall flash-attn
!pip install --no-build-isolation flash-attn==2.3.0

!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/TheBloke/dolphin-2.2.1-mistral-7B-GGUF/resolve/main/dolphin-2.2.1-mistral-7b.Q5_K_M.gguf?download=true -d /content/text-generation-webui/models/ -o dolphin-2.2.1-mistral-7b.Q5_K_M.gguf

%cd /content/text-generation-webui
!python server.py --share --n-gpu-layers 1000000000 --model dolphin-2.2.1-mistral-7b.Q5_K_M.gguf