apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Support include_stop_str_in_output in chat/completion (#2910)

Browse Source 
* [Feature] Support include_stop_str_in_output in chat/completion

* Add ci test for include_stop_str_in_output

* Update version of openai

* Fix ci test

---------

Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
This commit is contained in:
Jiang-Jia-Jun
2025-07-18 16:59:18 +08:00
committed by GitHub
parent 6efad14b95
commit fbe3547c95
5 changed files with 82 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
fastdeploy/input/text_processor.py
View File

@@ -355,7 +355,7 @@ class DataProcessor(BaseDataProcessor):
token_ids = response_dict["outputs"]["token_ids"]
is_end = response_dict["finished"]
req_id = response_dict["request_id"]
if is_end and len(token_ids) > 0:
if is_end and len(token_ids) > 0 and not kwargs.get("include_stop_str_in_output"):
if token_ids[-1] == self.tokenizer.eos_token_id:
token_ids = token_ids[:-1]
delta_text, _, previous_texts = self.ids2tokens(token_ids, req_id)
@@ -390,7 +390,7 @@ class DataProcessor(BaseDataProcessor):
req_id = response_dict["request_id"]
token_ids = response_dict["outputs"]["token_ids"]
if is_end and len(token_ids) > 0:
if is_end and len(token_ids) > 0 and not kwargs.get("include_stop_str_in_output"):
if token_ids[-1] == self.tokenizer.eos_token_id:
token_ids = token_ids[:-1]
delta_text, previous_token_ids, previous_texts = self.ids2tokens(
@@ -430,7 +430,7 @@ class DataProcessor(BaseDataProcessor):
response_dict, enable_thinking=enable_thinking, **kwargs)
else:
return self.process_response_dict_normal(
response_dict=response_dict, enable_thinking=enable_thinking)
response_dict=response_dict, enable_thinking=enable_thinking, **kwargs)
def text2ids(self, text, max_model_len, raw_request=True):
"""