[FIX BUG] UnboundLocalError: cannot access local variable 'default_co…

…nversation' where it is not associated with a value (hpcaitech#5931)

* cannot access local variable 'default_conversation' where it is not associated with a value

set default value for 'default_conversation'

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

applications/Colossal-LLaMA/prepare_sft_dataset.py

@@ -10,7 +10,7 @@
 import os
 from multiprocessing import cpu_count
 
-from colossal_llama.dataset.conversation import LLaMA2_Conv
+from colossal_llama.dataset.conversation import LLaMA2_Conv, LLaMA3_Conv
 from colossal_llama.dataset.spliced_and_tokenized_dataset import supervised_tokenize_sft
 from datasets import dataset_dict, load_dataset
 from transformers import AddedToken, AutoTokenizer
@@ -75,6 +75,8 @@ def main():
     # Prepare to the tokenizer.
     tokenizer = AutoTokenizer.from_pretrained(args.tokenizer_dir)
 
+    default_conversation = LLaMA3_Conv
+
     # Fix </s> split issue: https://github.com/huggingface/transformers/issues/23833
     if args.llama_version == 2:
         tokenizer.add_tokens(AddedToken("</s>", normalized=False, special=True), special_tokens=True)