Repository navigation
feat(serve): default the sampling temperature to 1.0 in both thinking… - #333
Merged
Merged
Conversation
… states A request that sends no sampling takes the table's values, and the instruct rows were 0.7 — flatter, shorter answers than the same model in thinking mode. Use 1.0 for both states in every family; top_p, top_k and presence_penalty stay as they were. Requests and configs that ask for a temperature still win, and an explicit temperature 0 is still greedy. The table no longer mirrors the Qwen cards' instruct column; the comment says so.
|
This pull request is labeled
|
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
… states
A request that sends no sampling takes the table's values, and the instruct rows were 0.7 — flatter, shorter answers than the same model in thinking mode. Use 1.0 for both states in every family; top_p, top_k and presence_penalty stay as they were. Requests and configs that ask for a temperature still win, and an explicit temperature 0 is still greedy.
The table no longer mirrors the Qwen cards' instruct column; the comment says so.
What & why
Fixes #
Area
edge0-infer/)edge0-infer/tools/assets/)edge0-infer/examples/)docs/)edge0-strata/How was it tested?
Checklist
ctest --preset cpu -L "L0|L1"passes locally inedge0-infer/(engine changes); CI also runs these and theL2tests not labeledlocal-onlylocal-onlyanswer suites (ctest --preset cpu -L local-only) on Apple silicon with i8mm (M2 or later), which CI cannot judgeedge0-infer/docs/testing.md)