# ChenmienTan/RL2

Repository: https://github.com/ChenmienTan/RL2
Canonical: https://ross.abutalabs.com/products/rl2
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-05-20T08:28:37+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 35, longevity 36
- inputs: {"age_days": 516, "days_push": 105, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1307, forks 135 (observed 2026-08-28T04:04:18.958251+00:00)

## What it is
RL2 (Ray Less Reinforcement Learning) is a concise Python library for post-training large language models with reinforcement learning, SFT, RM, and DPO. It offers a clear, low-abstraction implementation while scaling via FSDP and Megatron 3D/5D parallelism and multi-turn rollout with SGLang.

## Use cases
- train an LLM with reinforcement learning post-training
- run SFT fine-tuning on custom datasets
- train reward models or run DPO alignment
- quickly prototype a new RL algorithm for LLMs
- scale RL training across multiple GPUs with parallelism
- run multi-turn agentic rollouts with SGLang

## When to choose
- you want a readable, low-abstraction RLHF/RL training codebase to learn from or modify
- you need quick experiments on RL post-training algorithms
- you need scalable training with FSDP or Megatron parallelism
- you want agentic environment rollouts via GEM and SGLang

## When to avoid
- you need a fully turnkey enterprise training platform with extensive abstractions
- you require LoRA/PEFT support, which is not yet implemented
- your workflow depends on Ray-based orchestration

## Facets
- artifact type: library
- maturity: active
- function: llm-training, machine-learning, gpu-computing, benchmarking
- domain: large-language-models, machine-learning, deep-learning, reinforcement-learning
- platform: python
- tags: reinforcement-learning, post-training, sft, dpo, rlhf, fsdp, megatron, sglang, distributed-training, agentic-environments, gpu, docker, linux

## Member repositories
- ChenmienTan/RL2 (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.958251+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:50:07.217114+00:00, confidence not recorded.
  - readme: https://github.com/ChenmienTan/RL2 (fetched 2026-08-28T04:04:18.958251+00:00, sha 2cfc01d5788c)
- Data as of 2026-08-30T08:39:29.467469+00:00.