openrlhf-training
From the author
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.
Install
npx skills add KalarisLabs/research-agent-skills --skill openrlhf-training -a claude-code
Installs to .claude/skills/openrlhf-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
- Uses sudoLow
Why 80
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.
- verl-rl-trainingKalarisLabs/research-agent-skillsProvides 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.DevOps★ 76
- fine-tuning-with-trlKalarisLabs/research-agent-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★ 76
- axolotlOrchestra-Research/AI-Research-SKILLsExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal supportOther★ 14.1K
- unslothericrisco/rsc-harnessUse when fine-tuning an open-weight LLM fast on ONE GPU with low VRAM — Unsloth's fast model loaders with 4-bit QLoRA and the trl trainer, response-only loss masking so the prompt is not trained on, GRPO reasoning fine-tunes, and export to merged 16-bit, GGUF or the Hub. NOT whether, why or which method to fine-tune (that is `finetuning`), NOT running the exported GGUF locally (that is `ollama`), NOT serving-engine flags and throughput (that is `vllm`), NOT building the JSONL dataset (that is `training-data`).Other★ 383
- deepspeedOrchestra-Research/AI-Research-SKILLsExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attentionOther★ 14.1K
- 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
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in