github
/
ColossalAI
mirror of https://github.com/hpcaitech/ColossalAI
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[FIX BUG] UnboundLocalError: cannot access local variable 'default_conversation' where it is not associated with a value (#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>
pull/5934/head
zhurunhua 2024-07-21 19:46:01 +08:00 committed by GitHub
parent f585d4e38e
commit 4ec17a7cdf
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
applications/Colossal-LLaMA/prepare_sft_dataset.py
View File

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