Stars
Technical report of Kimina-Prover Preview.
FlashMLA: Efficient MLA decoding kernels
MoBA: Mixture of Block Attention for Long-Context LLMs
🤗 smolagents: a barebones library for agents that think in python code.
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…
The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis"
A python module to repair invalid JSON from LLMs
AnchorAttention: Improved attention for LLMs long-context training
Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Implementing Wordware's Twitter Personality Analysis (https://twitter.wordware.ai/) using APPL: A Prompt Programming Language (https://appl-team.github.io/appl/)
A series of math-specific large language models of our Qwen2 series.
Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]
Memory for AI Agents; SOTA in AI Agent Memory; Announcing OpenMemory MCP - local and secure memory management.
CSGO: Content-Style Composition in Text-to-Image Generation 🔥
Empowering everyone to build reliable and efficient software.
Reference implementation for Token-level Direct Preference Optimization(TDPO)
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"