facebookresearch / Pearl
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
☆2,766Updated last week
Alternatives and similar repositories for Pearl:
Users that are interested in Pearl are comparing it to the libraries listed below
- PyTorch native post-training library☆4,856Updated this week
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆5,790Updated 2 months ago
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-…☆3,266Updated last week
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,731Updated 2 months ago
- Tools for merging pretrained large language models.☆5,260Updated last week
- A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.☆2,537Updated this week
- Fine-tune LLM agents with online reinforcement learning☆1,065Updated 11 months ago
- Training LLMs with QLoRA + FSDP☆1,451Updated 3 months ago
- Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs☆2,362Updated last week
- ☆4,058Updated 8 months ago
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.☆507Updated 3 months ago
- Robust recipes to align language models with human and AI preferences☆5,001Updated 3 months ago
- Mastering Diverse Domains through World Models☆1,503Updated last week
- Stanford NLP Python library for Representation Finetuning (ReFT)☆1,418Updated 2 weeks ago
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,361Updated 10 months ago
- Modeling, training, eval, and inference code for OLMo☆5,200Updated this week
- A curated list of reinforcement learning with human feedback resources (continually updated)☆3,729Updated this week
- A framework for few-shot evaluation of language models.☆7,848Updated this week
- Really Fast End-to-End Jax RL Implementations☆810Updated 5 months ago
- Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors a…☆1,283Updated this week
- A PyTorch native library for large model training☆3,326Updated this week
- Train transformer language models with reinforcement learning.☆11,782Updated this week
- ☆2,852Updated 5 months ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,251Updated 2 months ago
- Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"☆2,282Updated 2 months ago
- NanoGPT (124M) in 3 minutes☆2,294Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,448Updated this week
- Monte Carlo tree search in JAX☆2,426Updated 2 months ago
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆11,592Updated this week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,230Updated last week