Skip to content

GitLab

"csrc/cpu/diag_cpu.cpp" did not exist on "64b0ae3041b05dc6c9c42484dbad01c3b6bc5cd1"
Commit 4d85af94 authored by Allen Wang's avatar Allen Wang Committed by A. Unique TensorFlower
Browse files

Fix command in XLNet README. 

PiperOrigin-RevId: 337366497
parent 0ca9cd6a
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
official/nlp/xlnet/README.md
View file @ 4d85af94
......@@ -98,7 +98,7 @@ export IMDB_DIR=~/imdb
mkdir -p ${IMDB_DIR}
cd ${IMDB_DIR}
wget http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz .
wget http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz
tar zxvf aclImdb_v1.tar.gz -C ${IMDB_DIR}
rm aclImdb_v1.tar.gz
```
......@@ -108,7 +108,7 @@ Then, the dataset can be converted into TFRecords with the following command:
```shell
export TASK_NAME=imdb
python3 preprocess_classification_data.py --max_seq_length=512 --spiece_model_file=${SPIECE_MODEL} --output_dir=${DATASETS_DIR}/${TASK_NAME} --data_dir=${IMDB_DIR} --task_name=${TASK_NAME}
python3 preprocess_classification_data.py --max_seq_length=512 --spiece_model_file=${SPIECE_MODEL} --output_dir=${DATASETS_DIR}/${TASK_NAME} --data_dir=${IMDB_DIR}/aclImdb --task_name=${TASK_NAME}
```
Note: To obtain SOTA on the IMDB dataset, using a sequence length of 512 is
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment