Chunking for confidence if context exceeds context length #635
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
rajasbansal
requested review from
nihit,
yadavsahil197 and
Abhinav-Naikawadi
nihit
approved these changes
Nov 20, 2023
| """Returns the number of tokens in the prompt""" | ||
| return len(self.confidence_tokenizer.encode(str(inp))) | ||
|
|
||
| def chunk_string(self, inp: str, chunk_size: int) -> List[str]: |
There was a problem hiding this comment.
uses the tokenizer, for encoding and decoding so kept it here
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Outdated suggestions cannot be applied.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.
In this PR, we will chunk confidence prompts in order to support getting confidence from a model having context length smaller than the context length supported by the generation model. We do this by chunking the document into smaller chunks and sending the prompt along with the smaller chunks of the document. we support multiple aggregation functions over the confidence chunks.
For extraction, max makes more sense than mean which might make more sense for a classification task