#!/bin/bash
echo "Export params ..."

export HIP_VISIBLE_DEVICES=0,1,2,3 # 自行修改为训练的卡号和数量
export HSA_FORCE_FINE_GRAIN_PCIE=1
export USE_MIOPEN_BATCHNORM=1


echo "Start ..."
# Meta-Llama-3-8B-Instruct 模型
torchrun --nproc_per_node 1 example_chat_completion.py \
    --ckpt_dir ./Meta-Llama-3-8B-Instruct/original/ \
    --tokenizer_path ./Meta-Llama-3-8B-Instruct/original/tokenizer.model \
    --max_seq_len 512 --max_batch_size 6

# Meta-Llama-3-8B 模型
torchrun --nproc_per_node 1 example_text_completion.py \
    --ckpt_dir Meta-Llama-3-8B/original/ \
    --tokenizer_path Meta-Llama-3-8B/original/tokenizer.model \
    --max_seq_len 128 --max_batch_size 4