# CarperAI/trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Repository: https://github.com/CarperAI/trlx
Canonical: https://ross.abutalabs.com/products/trlx
Language: Python
License: MIT
License Family: permissive
Topics: machine-learning, pytorch, reinforcement-learning
Last push: 2024-01-08T20:07:19+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1430, "days_push": 968, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4755, forks 486 (observed 2026-08-28T04:08:58.850783+00:00)

## What it is
trlX is a distributed training framework for fine-tuning large language models with reinforcement learning from human feedback (RLHF), supporting PPO and ILQL algorithms. It provides Accelerate-backed trainers for models up to 20B parameters and NVIDIA NeMo-backed trainers for larger models.

## Use cases
- fine-tune an LLM with RLHF using a reward function
- train a 20B parameter language model with PPO
- apply ILQL to a reward-labeled dataset
- distributed RL fine-tuning of GPT-NeoX or Flan-T5
- align a language model with human preferences

## When to choose
- you need distributed RLHF training for large causal or T5-based language models
- you want PPO or ILQL implementations on top of Hugging Face models
- you need to scale fine-tuning beyond 20B parameters with NeMo

## When to avoid
- you only need supervised fine-tuning without reinforcement learning
- you want actively maintained tooling - the project is in maintenance mode and TRL is the more active successor
- you work outside the PyTorch/Hugging Face ecosystem

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-training, machine-learning, reinforcement-learning
- domain: large-language-models, reinforcement-learning, machine-learning, deep-learning
- platform: python
- tags: rlhf, ppo, ilql, distributed-training, pytorch, huggingface, nemo, fine-tuning, gpu, linux

## Member repositories
- CarperAI/trlx (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:58.850783+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 2026-08-29T18:18:53.522918+00:00, confidence not recorded.
  - readme: https://github.com/CarperAI/trlx (fetched 2026-08-28T04:08:58.850783+00:00, sha 2873791643e9)
- Data as of 2026-08-30T08:39:29.467469+00:00.