trl-training

Name: trl-training
Author: waybarrios

SKILLWorkflowcommunity

v0.0.0waybarriosMITUpdated 2d agoSource →

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →

470Repo stars

1Clients

1Formats

2d agoLast update

Skill

Authorwaybarrios

Version0.0.0

LicenseMIT

CategoryWorkflow

Formatsskill.md

PromptNot published

Compatibility

Claude✓ Supported

Cursor—

Copilot—

ChatGPT—

Gemini—

About

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

Keywords

skillclaude