server: extract <think> tags from qwq outputs
#12297
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ggerganov
reviewed
Mar 10, 2025
common/chat.cpp
Outdated
Comment on lines
1126
to
1128
| static std::regex function_regex("<｜tool▁call▁begin｜>function<｜tool▁sep｜>([^\n]+)\n```json\n"); | ||
| static std::regex close_regex("```[\\s\\r\\n]*<｜tool▁call▁end｜>"); | ||
| static std::regex tool_calls_regex("[\\s\\r\\n]*(?:<｜tool▁calls▁begin｜>|<｜tool_calls_begin｜>|<｜tool calls begin｜>|<｜tool\\\\_calls\\\\_begin｜>)([\\s\\S\\r\\n]*?)<｜tool▁calls▁end｜>"); |
ngxson
approved these changes
Mar 10, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #12275
Note: unrelated to this PR, but streaming mode is still not dealing w/ thoughts extraction, which means templates that pre-feed the
<think>tag (like DeepSeek R1 Distills & QwQ-32B) will lack the<think>tag in their output. Will address separately w/ a streaming overhaul + tool call support.