Fix the penultimate token sometimes being lost with SSE streaming#1031
Merged
LostRuins merged 4 commits intoLostRuins:concedo_experimentalfrom Jul 29, 2024
Merged
Conversation
Merge upstream
Merge upstream
Merge upstream
The token immediately before an eot token was lost when SSE streaming was enabled if that token was contained entirely within a stop sequence. As an example of when this could happen, consider this prompt: Type the phrase 'pleas' once. In a Llama 3-derived model, 'pleas' tokenizes as 'ple' 'as'. The token 'as' is contained within this instruct mode stop sequence: <|eot_id|><|start_header_id|>assistant<|end_header_id|> due to the word 'assistant'. Since `string_contains_sequence_substring` returns True for 'as', this token is added to `tokenReserve` instead of being streamed immediately. If the '<|eot_id|>' token was generated next, the text in `tokenReserve` would be discarded.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The token immediately before an eot token was lost when SSE streaming was enabled if that token was contained entirely within a stop sequence. As an example of when this could happen, consider this prompt:
In a Llama 3-derived model, 'pleas' tokenizes as 'ple' 'as'. The token 'as' is contained within this instruct mode stop sequence:
<|eot_id|><|start_header_id|>assistant<|end_header_id|>due to the word 'assistant'. Sincestring_contains_sequence_substringreturnsTruefor 'as', this token is added totokenReserveinstead of being streamed immediately. If the '<|eot_id|>' token was generated next, the text intokenReservewould be discarded.