Make it work for realz

This commit is contained in:
Lewis Tunstall
2023-11-08 22:20:17 +00:00
parent d2900adc83
commit e54e095978
4 changed files with 102 additions and 3 deletions
+3 -3
View File
@@ -90,9 +90,9 @@ def main():
for index in random.sample(range(len(raw_datasets["train"])), 3):
logger.info(f"Sample {index} of the raw training set:\n\n{raw_datasets['train'][index]['messages']}")
#####################################
# Load tokenizer and process datasets
#####################################
################
# Load tokenizer
################
tokenizer = get_tokenizer(model_args, data_args)
#####################