awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
lucidrains avatar

lucidrains/PaLM-rlhf-pytorch

0
View on GitHub↗
7,863 stars·676 forks·Python·MIT·25 views

PaLM Rlhf Pytorch

This is a PyTorch implementation of reinforcement learning from human feedback designed to align large language models with human values and preferences. It provides a framework for the PaLM architecture and incorporates parameter-efficient fine-tuning to adapt models while minimizing the number of updated weights.

The system enables the development of reward models that act as scoring mechanisms built from human preference data. These models evaluate generative outputs to guide the alignment process.

The workflow covers policy optimization using a clipped objective, reward modeling based on preference pairs, and the use of divergence penalties to keep the tuned model close to the original reference. It includes a transformer-based policy architecture and a buffer for sampling generated rollouts.

Features

  • Reinforcement Learning Alignment - Implements a complete reinforcement learning alignment workflow for large language models using PPO.
  • Reward Modeling - Implements reward modeling to train a scoring network that predicts human preferences between text samples.
  • Transformer Architectures - Employs a decoder-only transformer architecture as the policy network for token generation and log-probability computation.
  • Preference-Based Model Alignments - Refines model behavior using reinforcement learning based on curated human preference data for safer and more helpful responses.
  • PPO Implementations - Uses Proximal Policy Optimization with a clipped surrogate objective to ensure stable policy updates.
  • RLHF Implementations - Provides a complete PyTorch implementation of the RLHF process to refine generative model responses.
  • RLHF PyTorch Frameworks - Ships a full RLHF framework built on PyTorch for aligning large language models.
  • KL-Divergence Penalties - Provides a KL-divergence penalty to prevent reward hacking by keeping the tuned model close to the original reference.
  • Experience Replay Buffers - Implements experience replay buffers to decouple rollout sampling from gradient updates during reinforcement learning.
  • Language Model Architectures - Implements a language model based on the PaLM architecture for scalable text generation.
  • Parameter Efficient Fine-Tuning - Uses parameter-efficient fine-tuning to adapt the PaLM architecture while minimizing the number of updated weights.
  • Open Source Models - Implements reinforcement learning for large language models.
  • Research Implementations - PyTorch implementation of the PaLM architecture for RLHF.

Star history

Star history chart for lucidrains/palm-rlhf-pytorchStar history chart for lucidrains/palm-rlhf-pytorch

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Projects sharing features with PaLM Rlhf Pytorch

These projects share indexed features with PaLM Rlhf Pytorch. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • openrlhf/openrlhfOpenRLHF avatar

    OpenRLHF/OpenRLHF

    9,675View on GitHub↗

    OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across distributed GPU clusters. It provides tools for aligning large language models and multimodal vision-language models using algorithms such as PPO, GRPO, and DPO. The framework distinguishes itself through a distributed inference engine that overlaps sample rollout with training to increase throughput. It supports scaling to models exceeding 70 billion parameters via parameter sharding and handles long-context sequences through ring-attention sequence parallelism. The project

    Pythonlarge-language-modelsopenai-o1proximal-policy-optimization
    View on GitHub↗9,675
  • inclusionai/arealinclusionAI avatar

    inclusionAI/AReaL

    3,559View on GitHub↗

    AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a framework for developing multi-turn reasoning agents and training large models using reinforcement learning from human feedback. The project implements a toolkit for improving the visual reasoning and geometry problem solving capabilities of vision-language models. It utilizes a memory-efficient tuning system to optimize mathematical and reasoning models across different inference backends. The infrastructure supports large-scale training through tensor, pipeline, and expert p

    Pythonagentllmllm-agent
    View on GitHub↗3,559
  • openmanus/openmanus-rlOpenManus avatar

    OpenManus/OpenManus-RL

    3,916View on GitHub↗

    OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language models as agents. It serves as an agentic reasoning optimizer and reward model trainer, providing the infrastructure to improve model decision-making through reward-based policy optimization. The project distinguishes itself through a distributed architecture that supports parameter sharding across multiple compute nodes and a coordinated rollout system for collecting interaction trajectories. It incorporates advanced reasoning strategies, such as Tree-of-Thoughts and Monte Ca

    Python
    View on GitHub↗3,916
  • verl-project/verlverl-project avatar

    verl-project/verl

    22,000View on GitHub↗

    This project is a distributed training infrastructure designed for aligning large language models through reinforcement learning. It functions as an end-to-end engine for complex alignment tasks, including proximal policy optimization, direct preference optimization, and iterative self-play. By providing a unified framework for multi-turn interactions and tool-use scenarios, it enables the development of models capable of reasoning and external environment engagement. The framework distinguishes itself through a decoupled architecture that separates model training from sample generation. This

    Python
    View on GitHub↗22,000
Compare all 30 related projects→

Frequently asked questions

What does lucidrains/palm-rlhf-pytorch do?

This is a PyTorch implementation of reinforcement learning from human feedback designed to align large language models with human values and preferences. It provides a framework for the PaLM architecture and incorporates parameter-efficient fine-tuning to adapt models while minimizing the number of updated weights.

What are the main features of lucidrains/palm-rlhf-pytorch?

The main features of lucidrains/palm-rlhf-pytorch are: Reinforcement Learning Alignment, Reward Modeling, Transformer Architectures, Preference-Based Model Alignments, PPO Implementations, RLHF Implementations, RLHF PyTorch Frameworks, KL-Divergence Penalties.

Which projects share features with lucidrains/palm-rlhf-pytorch?

Projects with overlapping indexed features include: openrlhf/openrlhf — OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across… inclusionai/areal — AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a… openmanus/openmanus-rl — OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language… verl-project/verl — This project is a distributed training infrastructure designed for aligning large language models through… hiyouga/chatglm-efficient-tuning — ChatGLM-Efficient-Tuning is a fine-tuning framework and toolkit designed to optimize large language models using… hiyouga/llama-efficient-tuning — This project is a fine-tuning framework and training pipeline designed to optimize and adapt large language and vision…