openrlhf-training

openrlhf-training is a skill for Claude Code from liortesta/ClawdAgent. It costs 72 tokens per session (2,537 once invoked), scanned B, a copy of openrlhf-training, Apache-2.0.

A framework for training large language models with human feedback and related methods, using Ray for distributed computing and vLLM for faster model responses. RLHF is a way to adjust a model using human preferences.

In plain words
What is it for?
Use it for PPO, GRPO, RLOO, or DPO training of large models, with distributed jobs, GPU sharing, and vLLM-based inference.
Why use it?
It provides a setup for training large models across multiple GPUs and machines instead of managing each training component separately.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is --save_path ./output/llama3-8b-rlhf \.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for openrlhf-training

README.md
[![agentmods](https://agentmods.dev/badge/skills/liortesta/clawdagent/openrlhf.svg)](https://agentmods.dev/skills/liortesta/clawdagent/openrlhf)
Your own site
<a href="https://agentmods.dev/skills/liortesta/clawdagent/openrlhf"><img src="https://agentmods.dev/badge/skills/liortesta/clawdagent/openrlhf.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,537 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.02537
Opus 5 $0.00036 $0.01269
Sonnet 5 $0.00014 $0.00507
Haiku 4.5 $0.00007 $0.00254

Measured 6d ago against content hash eb9da6a1a81c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

openrlhf-training scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo pip uninstall xgboost transformer_engine flash_attn pynvml -y
Origin

This is a copy

100% identical to openrlhf-training — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/06-post-training/openrlhf/SKILL.md · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenRLHF - High-Performance RLHF Training

Quick start

OpenRLHF is a Ray-based RLHF framework optimized for distributed training with vLLM inference acceleration.

Installation:

# Launch Docker container
docker run --runtime=nvidia -it --rm --shm-size="10g" --cap-add=SYS_ADMIN \
  -v $PWD:/openrlhf nvcr.io/nvidia/pytorch:25.02-py3 bash

# Uninstall conflicts
sudo pip uninstall xgboost transformer_engine flash_attn pynvml -y

# Install OpenRLHF with vLLM
pip install openrlhf[vllm]

PPO Training (Hybrid Engine):

ray start --head --node-ip-address 0.0.0.0 --num-gpus 8

ray job submit --address="http://127.0.0.1:8265" \
  --runtime-env-json='{"working_dir": "/openrlhf"}' \
  -- python3 -m openrlhf.cli.train_ppo_ray \
  --ref_num_nodes 1 --ref_num_gpus_per_node 8 \
  --reward_num_nodes 1 --reward_num_gpus_per_node 8 \
  --critic_num_nodes 1 --critic_num_gpus_per_node 8 \
  --actor_num_nodes 1 --actor_num_gpus_per_node 8 \
  --vllm_num_engines 4 --vllm_tensor_parallel_size 2 \
  --colocate_all_models \
  --vllm_gpu_memory_utilization 0.5 \
  --pretrain OpenRLHF/Llama-3-8b-sft-mixture \
  --reward_pretrain OpenRLHF/Llama-3-8b-rm-700k \
  --save_path ./output/llama3-8b-rlhf \
  --micro_train_batch_size 8 --train_batch_size 128 \
  --micro_rollout_batch_size 16 --rollout_batch_size 1024 \
  --max_epochs 1 --prompt_max_len 1024 --generate_max_len 1024 \
  --zero_stage 3 --bf16 \
  --actor_learning_rate 5e-7 --critic_learning_rate 9e-6 \
  --init_kl_coef 0.01 --normalize_reward \
  --gradient_checkpointing --packing_samples \
  --vllm_enable_sleep --deepspeed_enable_sleep

GRPO Training (Group Normalized Policy Optimization):

# Same command as PPO, but add:
--advantage_estimator group_norm

Common workflows

Workflow 1: Full RLHF pipeline (SFT → Reward Model → PPO)

Step 1: Train reward model (DPO):

deepspeed --module openrlhf.cli.train_rm \
  --save_path ./output/llama3-8b-rm \
  --save_steps -1 --logging_steps 1 \
  --eval_steps -1 --train_batch_size 256 \
  --micro_train_batch_size 1 --pretrain meta-llama/Meta-Llama-3-8B \
  --bf16 --max_epochs 1 --max_len 8192 \
  --zero_stage 3 --learning_rate 9e-6 \
  --dataset OpenRLHF/preference_dataset_mixture2_and_safe_pku \
  --apply_chat_template --chosen_key chosen \
  --rejected_key rejected --flash_attn --gradient_checkpointing

Read the full file on GitHub · 250 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 250 lines · 72 tokens per session scan B eb9da6a1a81c

Subscribe to this mod's changes

openrlhf-training is a skill published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 9d ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,537 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). It is 100% identical to openrlhf-training, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

openrlhf-training

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.

OpenLAIR/dr-claw · 72 tokens

grpo-rl-training

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

davila7/claude-code-templates · 26 tokens

verl-rl-training

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.

davila7/claude-code-templates · 51 tokens

fine-tuning-with-trl

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.

davila7/claude-code-templates · 69 tokens

grpo-rl-training

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

OpenLAIR/dr-claw · 26 tokens

fine-tuning-with-trl

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.

OpenLAIR/dr-claw · 69 tokens