V0.2.0 #30
Closed
V0.2.0 #30
Conversation
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
…ect format in OptoPrime.
…eGuide to return LLM's response directly.
Add Projection API.
… add_model_dump
- Update docstring format to avoid mkdocstrings parsing issues - Resolves 'Could not find cross-reference target' warnings in strict mode
…into experimental
…into experimental
Fix missing oprov2 problem
Adding a train helper function and updating defaults of MinibatchAlgorithm and LLMJudge
Upgrade to Python3.10
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Outdated suggestions cannot be applied.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.
Major milestone reached. Thanks to all the contributors!!
This update introduces the new Trainer class, which defines a new high-level api that optimize a given Module on a Dataset following a Guide, using a search algorithm based on Optimizer(s). Default trainers include SequentialUpdate, BestOfN, UCBSearch, and BeamSearch.
This update also adds improved implementation OptoPrimeV2 and OPROv2 for end-to-end and black-box optimization tasks, respectively.
Improved core functionalities, interfaces, and various bug fixes.
See the roadmap for details. https://docs.google.com/spreadsheets/d/1dMoECd2Soj6bATpkNDeaMxl0ymOYCtGq7ZiHr0JRdJU/edit?gid=1252455422#gid=1252455422
Do not merge yet
TODO: adopt Priority Search as the base of trainers.
This branch now tracks the latest features/PR toward v0.2.0, which can be ahead
experimentalbranch