{
 "repo": "huggingface/trl",
 "url": "https://github.com/huggingface/trl",
 "what": "TRL is Hugging Face's library for post-training foundation models. It provides trainers for Supervised Fine-Tuning (SFT), GRPO, DPO, KTO and reward modeling on top of Transformers, scales from one GPU to multi-node clusters with Accelerate, integrates PEFT for LoRA and QLoRA, and ships a CLI that fine-tunes without writing code.",
 "language": "Python",
 "stars": null,
 "gain": null,
 "created": "",
 "uc_n": 3,
 "title": "TRL",
 "show": true,
 "what_source": "deduped",
 "use_cases": "https://dedupedai.com/use-cases/huggingface-trl/",
 "use_cases_json": "https://dedupedai.com/use-cases/r/huggingface-trl.json",
 "json": "https://dedupedai.com/repos/r/huggingface-trl.json",
 "slug": "huggingface-trl",
 "api": "https://dedupedai.com/api/v1/repos/huggingface-trl.json",
 "api_version": "v1"
}