domains / families / software-engineering / trl

trl

separate

Reference for the TRL (Transformer Reinforcement Learning) library codebase. Use proactively before reading or editing any file under `trl/` so you have the intended contracts and invariants in mind, not just what the current code says. Covers trainer hierarchy (SFT, DPO, GRPO, KTO), shared utility functions (selective_log_softmax, decode_and_strip_padding, padding helpers), configuration system, model wrappers, and how data flows through any TRL trainer.

When to use

• reading or editing files under trl/
• understanding trainer hierarchy (SFT, DPO, GRPO, KTO)
• reviewing shared utility functions
• checking configuration system fields
• inspecting model wrappers
• tracing data flow through TRL trainers

Skill page

Source