mirror of
https://github.com/ErlichLiu/DeepClaude.git
synced 2026-04-25 05:05:57 +03:00
[GH-ISSUE #9] 高效利用R1的剩余回答 #3
Labels
No labels
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
pull-request
question
wontfix
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
starred/DeepClaude#3
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @GowayLee on GitHub (Feb 4, 2025).
Original GitHub issue: https://github.com/ErlichLiu/DeepClaude/issues/9
项目基础功能好像实现得差不多啦🎉
但是... 感觉每次都截断只使用R1的推理过程有点浪费token.
🤯希望大家可以讨论一下如何高效利用R1的剩余回答
例如
@jiacheo commented on GitHub (Feb 5, 2025):
把 max_tokens 设置为 1 试试
@GowayLee commented on GitHub (Feb 5, 2025):
推理模型的思维链也算token, 刚刚试了一下, 发现这样会导致推理过程输出1token后直接停了
@ErlichLiu commented on GitHub (Feb 5, 2025):
是的,我也是尝试了一下,这个方案确实不太行,我们再想想其他的方案吧
@GowayLee commented on GitHub (Feb 5, 2025):
DeepSeek和SiliconFlow都支持在补全请求中设置
stop参数可以尝试用Prompt强迫模型在开口回答前先输出某一个特殊字符组合, 然后配合
stop参数来中止推理(之前可以很固定输出
</think>, 结果现在没有了😅)