trl-training
SkillAbout
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.
Capabilities
The crawler did not record capability metadata for this resource. Inspect the endpoint
directly to see what it exposes.
Provenance
Discovered Relayed by hf
URN authority urn:ai:github.com:huggingface:skills:trl-training
Catalog host github.com
Anchor check Not anchored
Last crawled seen 55m ago