Stars
Repo for paper "Agentic-R: Learning to Retrieve for Agentic Search" (ACL 2026 Findings)
Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"
Fully open reproduction of DeepSeek-R1
Repo for paper "ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability" (ACL 2026 Main)
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
Model Context Protocol Servers
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
Collection of leaked system prompts
FlashMLA: Efficient Multi-head Latent Attention Kernels
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
MAIR: A Massive Benchmark for Evaluating Instructed Retrieval. Evaluate your retrieval models on 126 diverse tasks. [EMNLP 2024]
The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.
A high-throughput and memory-efficient inference and serving engine for LLMs
JAILJUDGE: A comprehensive evaluation benchmark which includes a wide range of risk scenarios with complex malicious prompts (e.g., synthetic, adversarial, in-the-wild, and multi-language scenarios…
Code and data repository for two papers (ACL & EMNLP 2024) on the topic of collapse in model editing.
Open-Sora: Democratizing Efficient Video Production for All
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
The official PyTorch implementation of Google's Gemma models
The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".
The official GitHub page for the survey paper "A Survey of Large Language Models".
The RedPajama-Data repository contains code for preparing large datasets for training large language models.