yuyan-10b / megatron /data /test /test_preprocess_data.sh
Shawn001's picture
Upload 131 files
23bd7af
raw
history blame contribute delete
241 Bytes
#!/bin/bash
IMPL=cached
python ../preprocess_data.py \
--input test_samples.json \
--vocab vocab.txt \
--dataset-impl ${IMPL} \
--output-prefix test_samples_${IMPL} \
--workers 1 \
--log-interval 2