Update README.md

Guitaricet · Jan 4, 2024 · b7b7c58 · b7b7c58
1 parent c5094fc
commit b7b7c58
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -35,9 +35,9 @@ Pre-process data (might take some time)
 ```bash
 python pretokenize.py \
     --save_dir preprocessed_data \
-    --tokenizer <HF tokenizer name or path> \
-    --dataset <HF dataset id> \
-    --dataset_config <DatasetConfig> \
+    --tokenizer t5-base \
+    --dataset c4 \
+    --dataset_config en \
     --text_field text \
     --sequence_length 512
 ```