apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-23 16:44:22 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[fix]update apply_chat_template (#4249)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details

Browse Source 
* [fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test

* fix

* [fix]update apply_chat_template (#4137)

* update apply_chat_template

* fix unittest

* fix unittest

* fix

* fix

* fix unit test

* fix

* fix unit test

* add unit test
This commit is contained in:
luukunn
2025-09-25 16:41:56 +08:00
committed by GitHub
parent 8fdb950e9f
commit aebe12a58d
10 changed files with 146 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
fastdeploy/input/ernie4_5_vl_processor/process.py
View File

@@ -250,8 +250,8 @@ class DataProcessor:
"video",
]:
image_message_list.append(item)
prompt_token_ids = self.apply_chat_template(request)
chat_template_kwargs = request.get("chat_template_kwargs", {})
prompt_token_ids = self.apply_chat_template(request, **chat_template_kwargs)
if len(prompt_token_ids) == 0:
raise ValueError("Invalid input: prompt_token_ids must be a non-empty sequence of token IDs")
image_start_index = 0
@@ -480,7 +480,7 @@ class DataProcessor:
break
self.tokenizer = Ernie4_5Tokenizer.from_pretrained(self.model_name_or_path)
def apply_chat_template(self, request):
def apply_chat_template(self, request, **kwargs):
"""
Convert multi-turn messages into ID sequences.
@@ -498,7 +498,7 @@ class DataProcessor:
request,
tokenize=False,
add_generation_prompt=request.get("add_generation_prompt", True),
chat_template=request.get("chat_template", None),
**kwargs,
)
prompt_token_str = prompt_token_template.replace("<|image@placeholder|>", "").replace(
"<|video@placeholder|>", ""