Named tools and model families · MLD-1272
TRL
A library supporting language-model post-training methods such as supervised and preference-based training.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Run a DPO training workflow.
Original caveat
Not every method in TRL is reinforcement learning.
Context and aliases
Level: Intermediate. Stages: Training · Adaptation · Deployment.
Tags: LLM · SLM · RL.
Aliases: Transformer Reinforcement Learning library.
Related concepts
Original references
- TRL documentation ↗ · Consulted
- Original reference URL ↗