Repository navigation
Add GemmaModel.score_next to the Python binding. - #1053
Merged
Merged
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
copybara-service
Bot
force-pushed
the
test_996092908
branch
5 times, most recently
from
October 12, 2026 15:37
060962c to
7cd5c67
Compare
score_next(prompt, candidates) returns, for each candidate string, the probability that the next token after the prompt is that candidate's first token, from the full-vocabulary softmax (ops-inl.h Softmax) of the next-token logits. It uses RuntimeConfig::sample_func for one decode step and restores the config afterwards. get_last_prob() cannot serve this: with the default top_k == 1 it reports the softmax over the top-1 token, so it is always 1.0. PiperOrigin-RevId: 997943475
copybara-service
Bot
force-pushed
the
test_996092908
branch
from
October 12, 2026 15:46
7cd5c67 to
e9da305
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add GemmaModel.score_next to the Python binding.
score_next(prompt, candidates) returns, for each candidate string, the
probability that the next token after the prompt is that candidate's first
token, from the full-vocabulary softmax (ops-inl.h Softmax) of the next-token
logits. It uses RuntimeConfig::sample_func for one decode step and restores the
config afterwards. get_last_prob() cannot serve this: with the default
top_k == 1 it reports the softmax over the top-1 token, so it is always 1.0.