FAIR Sequence Modeling Toolkit 2
Repository Index
132,241 visible repositories in the index
145–168 of 277 · Most stars
Reinforcement Learning via Self-Distillation (SDPO)
- distillation
- llm
- reasoning
- rl
[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)
- rl
- agentic-rl
- reinforcement-learning
- reinforcement-learning-agent
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
- machine-learning
- pytorch
- contrastive-learning
- neuroscience-methods
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
- llm
- reasoning
- rl
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.
Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo
- albert
- bart
- bert
- chinese
🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support
- llm
- vlm
- finetuning
- gemma3
A pytorch adversarial library for attack and defense methods on images and graphs
- adversarial-attacks
- adversarial-examples
- deep-neural-networks
- defense
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Dynamiq is an orchestration framework for agentic AI and LLM applications
A version of verl to support diverse tool use [TMLR 2026]
Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.
Tutel MoE: Optimized Mixture-of-Experts Library, Support GLM/Kimi/Gpt/DeepSeek/Qwen using FP8/NVFP4/MXFP4
OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
- commonsense-reasoning
- deep-learning
- deep-neural-networks
- instruction-tuning
Metric learning and retrieval pipelines, models and zoo.
- computer-vision
- data-science
- deep-learning
- metric-learning
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
- speech-quality
- deep-learning
- interspeech
- icassp
Local-first AI teammate workspace. Bring your own models and keep project conversations, tool approvals, and results together.
An Automatic Prompt Optimization Framework for Large Language Models
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
- reinforcement-learning
- deep-reinforcement-learning
- deep-learning
- machine-learning
The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.
- agent-orchestration
- agent-workflow
- ai-agents
- claude-code-plugin
Deep reinforcement learning GPU libraries for NVIDIA Jetson TX1/TX2 with PyTorch, OpenAI Gym, and Gazebo robotics simulator.