This commit is contained in:
YeAnbang
2024-07-18 07:54:11 +00:00
parent b3594d4d68
commit 09d5ffca1a
27 changed files with 1739 additions and 63 deletions

View File

@@ -1,13 +1,13 @@
SAVE_DIR=""
SAVE_DIR="/home/nvme-share/home/yeanbang/data/experiments/sft"
rm -rf $SAVE_DIR/cache
rm -rf $SAVE_DIR/jsonl
rm -rf $SAVE_DIR/arrow
python prepare_dataset.py --type sft \
--data_input_dirs /PATH/TO/SFT/DATASET \
--conversation_template_config /PATH/TO/CHAT/TEMPLATE/CONFIG.json \
--tokenizer_dir "" \
--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_cache_dir $SAVE_DIR/cache \
--data_jsonl_output_dir $SAVE_DIR/jsonl \
--data_arrow_output_dir $SAVE_DIR/arrow \