-
Notifications
You must be signed in to change notification settings - Fork 623
[fix]Modify follow-up push parameters and Modify the verification method for thinking length #4086
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.
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
Conversation
Thanks for your contribution! |
if metadata and metadata.get("generated_token_ids"): | ||
self.append_generated_tokens(outputs, metadata["generated_token_ids"]) | ||
if metadata and metadata.get("completion_token_ids"): | ||
self.append_completion_tokens(outputs, metadata["completion_token_ids"]) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
本次修改去掉metadata, 直接从 request 中取。 需要再request 的 protocol 中增加该字段,同时修改 doc 文件。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
在 request 的 metadata 兼容的逻辑中, 如果metadata 不为空, 增加warnning 提示 此参数已经过时。
…hod for thinking length (PaddlePaddle#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
1.Modify the follow-up push parameter
generated_token_ids
tocompletion_token_ids
.2.Modify the verification method for
reasoning_max_tokens
so that whenreasoning_max_tokens
exceedsmax_tokens
, its value is set equal tomax_tokens
.