RLHFlow

Research codebase for RLHF reward modelling — pairwise / Bradley-Terry / pointwise reward heads; release of RewardBench-winning models.

Stale · Verified 2026-10-27 · fresh as of 2026-10-27 · 14 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Type: RLHF reward modelling toolkit repo fix
Tier: T4
Section: Training infrastructure
Created: 2024 repo fix
Latest release: no releases repo fix
License: Apache-2.0 repo fix
GitHub: RLHFlow/RLHF-Reward-Modeling — ~1.5k stars, last commit 2025-04 repo fix
Pricing: searched not found fix
Funding: searched not found fix
Freshness: 2026-10-27 fix
Layer: model-infra repo fix
Licensing: open-source repo fix
Deployment locus: local repo fix
Platform vs product: platform repo fix
Developer activity: OpenRank 0.09 (12-mo avg 2.45) · 1 participants — 2026-09 third-party fix

Optimised for: searched not found

Anti-fit: searched not found

searched not found

searched not found

searched not found

Other training infrastructure in the catalog, ranked by inbound references.

MLflow T1
Databricks-incubated open platform for ML lifecycle — tracking, projects, models, model registry. Standard ML-ops baseline. MLflow 3.0 (2024) added LLM-eval features.
AWS SageMaker T1
AWS's managed ML platform — Studio, Training, HyperPod (large-scale clusters), Endpoints. Industry-standard for enterprise AWS-hosted training.
Weights & Biases T1
Experiment-tracking and ML-ops platform (metrics, artifacts, sweeps, Weave tracing/evals). Acquired by CoreWeave (completed 2025-05-05, ~$1.7B); now part of CoreWeave Forge.
Comet ML T2
ML experiment tracking + LLM evaluation platform (Opik for LLM eval). Comet competes head-to-head with Weights & Biases.
Azure Machine Learning T1
Microsoft Azure's managed ML platform — pipelines, AutoML, Designer, prompt flow (LLM). Heavy integration with Azure OpenAI and Azure AI Studio.
LoRA T3
Microsoft Research's Low-Rank Adapters method — trains rank-r matrices added to attention weights; 10000x parameter reduction. Foundation of all adapter-style fine-tuning.

Each fact links to the page it came from; the badge says who published it (how to read sources).

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

2026-10-27
- Latest release first recorded as “no releases” source
- Deployment first recorded as “Self-hosted only — research codebase (training recipes)” source
#272