remove real data path

This commit is contained in:
YeAnbang
2024-07-22 06:11:38 +00:00
parent 12fe8b5858
commit b0e15d563e
6 changed files with 13 additions and 13 deletions

View File

@@ -5,9 +5,9 @@ rm -rf $SAVE_DIR/jsonl
rm -rf $SAVE_DIR/arrow
python prepare_dataset.py --type sft \
--data_input_dirs /home/nvme-share/home/yeanbang/data/dataset/hh_rlhf/sft \
--conversation_template_config /home/nvme-share/home/yeanbang/ColossalAI/applications/ColossalChat/config/conversation_template/llama2.json \
--tokenizer_dir "/home/nvme-share/share/models/Sheared-LLaMA-1.3B" \
--data_input_dirs /PATH/TO/SFT/DATASET \
--conversation_template_config /PATH/TO/CHAT/TEMPLATE/CONFIG.json \
--tokenizer_dir "" \
--data_cache_dir $SAVE_DIR/cache \
--data_jsonl_output_dir $SAVE_DIR/jsonl \
--data_arrow_output_dir $SAVE_DIR/arrow \