trl AI Agent Skills

grpo-rl-training

21.8k

davila7

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

fine-tuning-with-trl

21.8k

davila7

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

model_finetuning

39

vuralserhat86

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

tech_evaluation

5

mzniu

Provides a comprehensive technical assessment framework, including technology readiness level (TRL) ratings, scalability analysis, security reviews, and architecture design evaluations