app.py

output_dir = "/content/text-generation-webui/models/Llama-2-7b-Chat-GPTQ"

# Set the paths to the GPT-Q model files
config_json_path = os.path.join(output_dir, "config.json")
%cd /content
!apt-get -y install -qq aria2

!git clone -b v1.3 https://github.com/camenduru/text-generation-webui
%cd /content/text-generation-webui
!pip install -r requirements.txt
!pip install -U gradio==3.28.3

!mkdir /content/text-generation-webui/repositories
%cd /content/text-generation-webui/repositories
!git clone -b v1.2 https://github.com/camenduru/GPTQ-for-LLaMa.git
%cd GPTQ-for-LLaMa
!python setup_cuda.py install

# Download the GPT-Q model files
wget -O "${config_json_path}" "https://huggingface.co/4bit/Llama-2-7b-Chat-GPTQ/raw/main/config.json"
wget -O "${generation_config_json_path}" "https://huggingface.co/4bit/Llama-2-7b-Chat-GPTQ/raw/main/generation_config.json"
wget -O "${special_tokens_map_json_path}" "https://huggingface.co/4bit/Llama-2-7b-Chat-GPTQ/raw/main/special_tokens_map.json"
wget -O "${tokenizer_model_path}" "https://huggingface.co/4bit/Llama-2-7b-Chat-GPTQ/resolve/main/tokenizer.model"
wget -O "${tokenizer_config_json_path}" "https://huggingface.co/4bit/Llama-2-7b-Chat-GPTQ/raw/main/tokenizer_config.json"
wget -O "${gptq_model_path}" "https://huggingface.co/4bit/Llama-2-7b-Chat-GPTQ/resolve/main/gptq_model-4bit-128g.safetensors"

# Start the text generation web UI
python server.py --share --chat --wbits 4 --groupsize 128 --model_type llama