Skip to content

【OSPP】为防止模型翻译中断，添加结束符<<END>> #4593

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

【OSPP】为防止模型翻译中断，添加结束符<<END>> #4593

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions paddlex/inference/pipelines/components/prompt_engineering/generate_translate_prompt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,8 +165,9 @@ def generate_prompt(
if few_shot_demo_key_value_list:
few_shot_demo_key_value_list = f"\n这里是一些专业术语对照表,如果遇到对照表中单词要参考对照表翻译：\n{few_shot_demo_key_value_list}\n"

prompt = f"""{task_description}{rules_str}{output_format}{few_shot_demo_text_content}{few_shot_demo_key_value_list}"""

after_rule = "9. 请在翻译完成后添加特殊标记 <<END>>，确保翻译完整。"
prompt = f"""{task_description}{rules_str}{after_rule}{output_format}{few_shot_demo_text_content}{few_shot_demo_key_value_list}"""

language_name = language_map.get(language, language)
task_type = self.task_type
if task_type == "translate_prompt":
Expand Down
6 changes: 6 additions & 0 deletions paddlex/inference/pipelines/pp_doctranslation/pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -437,8 +437,14 @@ def translate_func(text):
few_shot_demo_key_value_list=few_shot_demo_key_value_list,
)
translate = chat_bot.generate_chat_results(prompt=prompt).get("content", "")

if "<<END>>" not in translate:
raise Exception("The translation did not reach the end. "
"This may happen if your chunk_size is too large. Please reduce chunk_size and try again.")
if translate is None:
raise Exception("The call to the large model failed.")

translate = translate.replace("<<END>>", "").rstrip()
return translate

base_prompt_content = self.translate_pe.generate_prompt(
Expand Down