MTEB: State-of-the-art evaluation of embeddings across languages and modalities
- benchmark
- clustering
- information-retrieval
- sentence-transformers
132,241 visible repositories in the index
145–168 of 809 · Most stars
MTEB: State-of-the-art evaluation of embeddings across languages and modalities
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
The next generation deep reinforcement learning tookit
Python script to update metadata information for items in plex as well as automatically build collections and playlists. The Wiki Documentation is linked below.
Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)
Modularized Implementation of Deep RL Algorithms in PyTorch
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
A high-performance distributed training framework for Reinforcement Learning
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning
Accelerated deep learning R&D
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
A collection of environments for autonomous driving and tactical decision-making tasks
Tensorforce: a TensorFlow library for applied reinforcement learning
Archivy is a self-hostable knowledge repository that allows you to learn and retain information in your own personal and extensible wiki.
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Tookie is a advanced OSINT information gathering tool that finds social media accounts based on inputs.
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
:satellite: Organized Resources for Deep Learning Researchers and Developers
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
TensorFlow Reinforcement Learning
Hands-on Deep Reinforcement Learning, published by Packt
Resources and Implementations of Generative Adversarial Nets: GAN, DCGAN, WGAN, CGAN, InfoGAN