P3O Experiments (Base, Hybrid, and more), integrations from dspy, docs changes#1
Open
LazyLogistics wants to merge 8 commits intomasterfrom
Open
P3O Experiments (Base, Hybrid, and more), integrations from dspy, docs changes#1LazyLogistics wants to merge 8 commits intomasterfrom
LazyLogistics wants to merge 8 commits intomasterfrom
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 goal of this pull request is to introduce p3o experiments, view docs to learn more about how to run them.
Added:
agent_torch/integrations -> adapter, utilities for experiment
experiments/ -> folder for base. hybrid experiments, and dependencies
docs/tutorials/running-an-experiment -> docs added for experiment usage **experiments/hybrid contains both baseline and round-robin files
Files altered:
agent_torch/core/llm/Variable.py -> Altered presentation choices and name hook to emulate experiment as closely as possible. Allow user to create a register Variable objects dynamically.
agent_torch/core/llm/mock_llm -> Now accepts structured data in the form of a dict; this is heavily important for calls which require more than one output per input including this experiment. Standardized flow of format using {response: dict} structure to allow for this behavior.
optim/p3o.py -> heavy changes to update in the format of experiment 2. Review /experiments to see usage.
TODO: Convert p3o experiments to a notebook -> will consider after experiment behavior is verified.