verl-rl-training
From the author
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.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill verl-rl-training -a claude-code
Installs to .claude/skills/verl-rl-training/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
No warnings.
Why 93
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- trl-traininghuggingface/skillsPost-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.OfficialWriting★ 11.2K
- grpo-rlvr-trainingwshobson/agentsTrain reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward functions, or when a GRPO run diverges or reward-hacks.Engineering★ 41.4K
- fine-tuning-with-trlOrchestra-Research/AI-Research-SKILLsFine-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.Other★ 13.8K
- openrlhf-trainingOrchestra-Research/AI-Research-SKILLsHigh-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.Planning★ 13.8K
- i4h-workflow-train-rlNVIDIA/skillsUse when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.Productivity★ 3.7K
- slime-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides 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.Other★ 13.8K
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in