cd Quark/examples/torch/language_modeling/llm_ptq/
export exclude_layers="lm_head *block_sparse_moe.gate* *self_attn*"
python3 quantize_quark.py --model_dir $MODEL_DIR \
                          --quant_scheme mxfp4 \
                          --num_calib_data 128 \
                          --exclude_layers $exclude_layers \
                          --skip_evaluation \
                          --multi_gpu  \
                          --trust_remote_code \
                          --model_export hf_format \
                          --output_dir $output_dir

export VLLM_ROCM_USE_AITER=1

export model_dir=MiniMaxAI/MiniMax-M2.5-MXFP4/
log_file=minimax25-lm_eval_gsm8k_mxfp4.txt

lm_eval --model vllm --model_args pretrained=$model_dir,enforce_eager=True,trust_remote_code=True,max_model_len=16384 \
        --gen_kwargs temperature=1.0,top_p=0.95,top_k=40 \
        --tasks gsm8k  --num_fewshot 8 2>&1 | tee $log_file