oklen
Follow
Stars
slime is an LLM post-training framework for RL Scaling.
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.
[NeurIPS 2025] Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
verl: Volcano Engine Reinforcement Learning for LLMs
Pure-Python Server Side Events (SSE) client
Best practices for distilling large language models.
Dromedary: towards helpful, ethical and reliable LLMs.
Offical Code for "PEVAE: A Hierarchical VAE for Personalized Explainable Recommendation."
A library for building and serving multi-node distributed faiss indices.
State-of-the-Art Text Embeddings
☕ A tool to generate requirements.txt for Python project, and more than that. (IT IS NOT A PACKAGE MANAGEMENT TOOL)
Library for Knowledge Intensive Language Tasks
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
Toolbox to integrate optimal transport loss functions using automatic differentiation and Sinkhorn's algorithm
SMedBERT: A Knowledge-Enhanced Pre-trained Language Model withStructured Semantics for Medical Text Mining
PyTorch package for the discrete VAE used for DALL·E.
Jupyter notebook on Gumbel-max and Gumbel-softmax tricks