post-training-grpo-rl-training
ComunidadMITExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
El ZIP contiene solo este skill. Está en GitHub Releases del repo público orlandoneto/agent-skills — Ontoom es la vitrina. El crawler diario actualiza el catálogo.
Cómo instalar
- Descarga el ZIP y extrae la carpeta del skill.
- Cursor:
.agents/skills/aitmpl-post-training-grpo-rl-training/o.cursor/skills/aitmpl-post-training-grpo-rl-training/ - Claude Code:
.claude/skills/aitmpl-post-training-grpo-rl-training/ - Otras IAs:
.agents/skills/aitmpl-post-training-grpo-rl-training/
Origen / créditos: davila7/claude-code-templates
Otros skills de esta colección
- post-training-miles
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
- post-training-openrlhf
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
- post-training-slime
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
- post-training-torchforge
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
- post-training-trl-fine-tuning
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.
- post-training-verl
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.