Trinity-RFT
Examples
Quick Start
Off-Policy RFT
Asynchronous RFT
Multi-Turn RFT
Offline DPO and SFT
Data Processing
Guidelines
Developer Guide
Configuration Guide
Algorithm Development
FAQ
FAQ
API Reference
trinity.buffer package
trinity.explorer package
trinity.trainer package
trinity.algorithm package
Subpackages
trinity.algorithm.advantage_fn package
trinity.algorithm.entropy_loss_fn package
trinity.algorithm.kl_fn package
trinity.algorithm.policy_loss_fn package
trinity.algorithm.sample_strategy package
Submodules
Module contents
trinity.manager package
trinity.common package
trinity.utils package
Trinity-RFT
trinity.algorithm package
trinity.algorithm.sample_strategy package
trinity.algorithm.sample_strategy.utils module
Edit on GitHub
trinity.algorithm.sample_strategy.utils module
trinity.algorithm.sample_strategy.utils.
representative_sample
(
experiences
:
List
[
Experience
]
)
→
List
[
dict
]
[source]
Other Versions
v: v0.2.0
Tags
v0.1.0
v0.1.1
v0.2.0
v0.2.1
Branches
main
(latest)