miles-rl-training

miles-rl-training is a skill for Claude Code from liortesta/ClawdAgent. It costs 51 tokens per session (2,424 once invoked), scanned A, a copy of miles-rl-training, Apache-2.0.

Guidance for using miles, a framework for training very large mixture-of-experts language models with reinforcement learning. It covers low-precision formats such as FP8 and INT4 and keeping training and model use closely aligned.

In plain words
What is it for?
Use it when training very large MoE models, using FP8 or INT4 quantization-aware training, matching training with inference, or applying speculative reinforcement learning.
Why use it?
Large models can be difficult to train reliably, especially when using reduced-precision numbers or many specialist parts. This explains approaches for stability, alignment, and faster model testing during training.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/liortesta/clawdagent/miles
Any agent
npx skills add liortesta/ClawdAgent --skill miles
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

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 miles-rl-training

README.md
[![agentmods](https://agentmods.dev/badge/skills/liortesta/clawdagent/miles.svg)](https://agentmods.dev/skills/liortesta/clawdagent/miles)
Your own site
<a href="https://agentmods.dev/skills/liortesta/clawdagent/miles"><img src="https://agentmods.dev/badge/skills/liortesta/clawdagent/miles.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,424 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00051 $0.02424
Opus 5 $0.00026 $0.01212
Sonnet 5 $0.00010 $0.00485
Haiku 4.5 $0.00005 $0.00242

Measured 5d ago against content hash cbf610faa37b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

miles-rl-training scanned grade A with 0 findings 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to miles-rl-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/miles/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

miles: Enterprise-Grade RL for Large-Scale Model Training

miles is a high-performance, enterprise-ready RL framework optimized for large-scale model post-training. Built as a production fork of slime, it addresses critical challenges in MoE training stability, low-precision training, and train-inference alignment.

When to Use miles

Choose miles when you need:

  • Training 1TB+ MoE models (DeepSeek V3, Qwen3-MoE)
  • FP8 or INT4 quantization-aware training
  • Bit-wise identical train-inference alignment
  • Speculative RL for maximum throughput
  • Production stability with enterprise support

Consider alternatives when:

  • You want the research-grade original → use slime
  • You need flexible backend swapping → use verl
  • You want PyTorch-native abstractions → use torchforge

Key Features

Low-Precision Training

  • Unified FP8: End-to-end FP8 for both inference and training
  • INT4 QAT: 1TB models on single-machine VRAM (H200)
  • Rollout Routing Replay (R3): Bit-wise expert alignment for MoE

Performance Optimizations

  • Speculative RL: 25%+ rollout speedup with online SFT draft models
  • Zero-Copy Weight Sync: CUDA IPC zero-copy mapping
  • Partial Rollout: Recycle half-finished trajectories

Train-Inference Alignment

  • TIS/MIS: Truncated/Masked Importance Sampling for off-policy correction
  • Kernel-level optimization: FlashAttention-3, DeepGEMM integration

Installation

# Recommended: Docker
docker pull radixark/miles:latest
docker run --rm --gpus all --ipc=host --shm-size=16g \
  -it radixark/miles:latest /bin/bash

# From source
git clone https://github.com/radixark/miles.git
cd miles
pip install -r requirements.txt
pip install -e .

Quick Start

miles inherits slime's configuration system. Basic training:

python train.py \
    --advantage-estimator grpo \
    --model-name qwen3-30b-a3b \
    --hf-checkpoint /path/to/qwen3-30b-a3b-hf \
    --rollout-batch-size 512 \
    --n-samples-per-prompt 8

Read the full file on GitHub · 316 lines

Files

What ships with it

2 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. 5d ago First seen · 316 lines · 51 tokens per session scan A cbf610faa37b

Subscribe to this mod's changes

miles-rl-training is a skill published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 9d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,424 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to miles-rl-training, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

miles-rl-training

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.

davila7/claude-code-templates · 51 tokens

miles-rl-training

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.

OpenLAIR/dr-claw · 51 tokens

miles-rl-training

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.

synthetic-sciences/openscience · 51 tokens

miles-rl-training

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.

Orchestra-Research/AI-Research-SKILLs · 51 tokens

miles-rl-training

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.

ihatesea69/HieuNghi-AI-Skills · 51 tokens

slime-rl-training

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.

davila7/claude-code-templates · 52 tokens