LnL-AI/

opt-125M-autoround-lm_head-false-symTrue

env CUDA_DEVICE_ORDER=PCI_BUS_ID CUDA_VISIBLE_DEVICES=0 python3 main.py \
--model_name facebook/opt-125M \
--device 0 \
--group_size 128 \
--bits 4 \
--seqlen 2048 \
--iters 1000 \
--use_quant_input \
--disable_eval \
--n_blocks 22 \
--sym \
--deployment_device 'gpu' \
--disable_low_gpu_mem_usage \
--output_dir "/monster/data/zx/opt-125M-quant_lm_head_false"