Open
Conversation
Introduce BinaryEncodedProcess, which wraps any GenerativeProcess by encoding its vocabulary into fixed-width big-endian binary. The wrapper emits individual bits (vocab_size=2) and defers the underlying state transition until a complete binary word has been emitted. Incomplete sequences are supported in probability/log_probability computations.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
BinaryEncodedProcess, a wrapper that encodes any generative process's vocabulary into fixed-width big-endian binary (MSB first)vocab_size=2) and defers the underlying state transition until a complete binary word is emittedprobability/log_probability(sequences may end mid-token)Test plan