conda create --name gptq python=3.9 -y
conda activate gptq
conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
# Or, if you're having trouble with conda, use pip with python3.9:
# pip3 install torch torchvision torchaudio

git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa
cd GPTQ-for-LLaMa
pip install -r requirements.txt

#convert LLaMA to hf
python convert_llama_weights_to_hf.py --input_dir /path/to/downloaded/llama/weights --model_size 7B --output_dir ./llama-hf

# Benchmark language generation with 4-bit LLaMA-7B:

# Save compressed model
CUDA_VISIBLE_DEVICES=0 python llama.py ${MODEL_DIR} c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save llama7b-4bit-128g.pt

# Or save compressed `.safetensors` model
CUDA_VISIBLE_DEVICES=0 python llama.py ${MODEL_DIR} c4 --wbits 4 --true-sequential --act-order --groupsize 128 --save_safetensors llama7b-4bit-128g.safetensors

# Benchmark generating a 2048 token sequence with the saved model
CUDA_VISIBLE_DEVICES=0 python llama.py ${MODEL_DIR} c4 --wbits 4 --groupsize 128 --load llama7b-4bit-128g.pt --benchmark 2048 --check

# Benchmark FP16 baseline, note that the model will be split across all listed GPUs
CUDA_VISIBLE_DEVICES=0,1,2,3,4 python llama.py ${MODEL_DIR} c4 --benchmark 2048 --check

# model inference with the saved model
CUDA_VISIBLE_DEVICES=0 python llama_inference.py ${MODEL_DIR} --wbits 4 --groupsize 128 --load llama7b-4bit-128g.pt --text "this is llama"

# model inference with the saved model using safetensors loaded direct to gpu
CUDA_VISIBLE_DEVICES=0 python llama_inference.py ${MODEL_DIR} --wbits 4 --groupsize 128 --load llama7b-4bit-128g.safetensors --text "this is llama" --device=0

# model inference with the saved model with offload(This is very slow).
CUDA_VISIBLE_DEVICES=0 python llama_inference_offload.py ${MODEL_DIR} --wbits 4 --groupsize 128 --load llama7b-4bit-128g.pt --text "this is llama" --pre_layer 16
It takes about 180 seconds to generate 45 tokens(5->50 tokens) on single RTX3090 based on LLaMa-65B. pre_layer is set to 50.

CUDA_VISIBLE_DEVICES=0 python llama.py ${MODEL_DIR} c4 --wbits 4 --true-sequential --act-order --groupsize 128 --quant-directory ${TOML_DIR}